© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 15996
    Prev
    Next
    INDEX
    Explanations

    follow up with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     immediate
    -0.10
     Replay
    -0.09
     Fried
    -0.09
     relay
    -0.09
    {:
    -0.09
     Challenge
    -0.09
     decre
    -0.09
    eni
    -0.09
     Immediate
    -0.09
     Paige
    -0.09
    POSITIVE LOGITS
     follow
    0.31
     Follow
    0.26
    Follow
    0.23
    follow
    0.22
     FOLLOW
    0.20
    -follow
    0.17
    _follow
    0.17
    .follow
    0.17
    åĤ¬
    0.16
     follows
    0.15
    Activations Density 0.087%

    No Known Activations