© 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. 61411
    Prev
    Next
    INDEX
    Explanations

    refused, unwilling, not

    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
     cant
    -0.12
    ushman
    -0.09
     ç©
    -0.09
    ued
    -0.09
     Kitt
    -0.09
     Gong
    -0.09
     Dump
    -0.08
     reward
    -0.08
    Insensitive
    -0.08
     Kut
    -0.08
    POSITIVE LOGITS
     refused
    0.26
     refuses
    0.25
     refuse
    0.25
     refusal
    0.23
     refusing
    0.22
     unwilling
    0.19
    ä¸įä¼ļ
    0.17
     não
    0.17
    æĭĴ
    0.17
     nicht
    0.17
    Activations Density 0.040%

    No Known Activations