Skip to content
View jfonsecarivera's full-sized avatar
55 followers · 11 following

Achievements

Achievement: Starstruckx2Achievement: Pull Shark

Achievements

Achievement: Starstruckx2Achievement: Pull Shark

Block or report jfonsecarivera

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jfonsecarivera/README.md

Joshua Fonseca Rivera

Anthropic Fellow working on interpretability, trying to figure out what is going on inside language models.

My most recent paper, Steering Awareness: Detecting Activation Steering from Within (COLM 2026), shows that models can be fine-tuned to detect and name steering vectors injected into their own activations.

Before research I spent several years as a software engineer. I studied Computer Science at the University of Chicago, specializing in Human-Computer Interaction, where I co-authored Touch&Fold (CHI 2021, Best Paper Honorable Mention).

jfr.dev · YouTube · X · LinkedIn

Pinned Loading

  1. vim-bujo vim-bujo Public

    A minimalist task manager for vim.

    Vim Script 206 15

  2. .vim .vim Public

    My Vim Repository

    Vim Script 4