© 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. 9773
    Prev
    Next
    INDEX
    Explanations

    default ChatGPT response

    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
     rhetorical
    -0.09
    URRED
    -0.08
    338
    -0.08
    _threads
    -0.08
     ngh
    -0.08
     retina
    -0.08
    ç»ĵåIJĪ
    -0.08
     disob
    -0.08
    rid
    -0.08
    ogg
    -0.07
    POSITIVE LOGITS
     response
    0.18
     answer
    0.16
     normal
    0.14
    response
    0.14
     usual
    0.13
    æŃ£å¸¸
    0.13
     réponse
    0.12
     Response
    0.12
     regular
    0.11
    answer
    0.11
    Activations Density 0.036%

    No Known Activations