© 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. 42016
    Prev
    Next
    INDEX
    Explanations

    providing information and appropriate answers

    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
    eso
    -0.10
     Yaz
    -0.10
     Cunning
    -0.10
     Gol
    -0.09
     Leon
    -0.09
     Pret
    -0.09
     Viet
    -0.09
     humility
    -0.09
     rhet
    -0.09
    aden
    -0.09
    POSITIVE LOGITS
     safe
    0.17
     neutral
    0.15
     PG
    0.14
    safe
    0.14
     neut
    0.13
     safest
    0.12
     general
    0.12
     Safe
    0.12
     safer
    0.12
     civil
    0.12
    Activations Density 0.136%

    No Known Activations