© 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. 57154
    Prev
    Next
    INDEX
    Explanations

    socially unbiased and positive

    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
    afone
    -0.09
    udoku
    -0.09
    ulk
    -0.09
    azo
    -0.09
    ERIC
    -0.09
    roz
    -0.08
    ARSE
    -0.08
    itan
    -0.08
    olest
    -0.08
    332
    -0.08
    POSITIVE LOGITS
    ness
    0.15
    -neutral
    0.11
    uos
    0.10
    uary
    0.09
    Neutral
    0.09
    ãĤĽ
    0.09
     neutral
    0.09
     doz
    0.09
    åĪ»
    0.09
    ly
    0.09
    Activations Density 0.012%

    No Known Activations