© 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. 2471
    Prev
    Next
    INDEX
    Explanations

    re agent, inate un, to any, turns 44

    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
    itti
    -0.10
     Pais
    -0.10
    acman
    -0.09
    ouncer
    -0.09
     Bene
    -0.09
     Slut
    -0.08
    Re
    -0.08
     иÑĤог
    -0.08
     Halk
    -0.08
    ataka
    -0.08
    POSITIVE LOGITS
     ï¾
    0.10
    789
    0.09
    à¸Ńà¸Ļà¸Ķ
    0.09
     needy
    0.09
     Wan
    0.09
    оне
    0.08
    _,,
    0.08
    @qq
    0.08
    æ£ļ
    0.08
     Nak
    0.08
    Activations Density 0.000%

    No Known Activations