© 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. 39550
    Prev
    Next
    INDEX
    Explanations

    regal, reggaeton, regression, region, rules

    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
    235
    -0.09
    stice
    -0.09
    icate
    -0.09
     fac
    -0.09
     unt
    -0.09
     Fine
    -0.09
    INGER
    -0.09
    ennent
    -0.09
    ablish
    -0.08
    ary
    -0.08
    POSITIVE LOGITS
    lement
    0.15
    aining
    0.13
    rett
    0.13
    ensburg
    0.13
    inal
    0.13
    .MustCompile
    0.13
    ional
    0.12
    eln
    0.12
    onal
    0.12
    azzi
    0.12
    Activations Density 0.026%

    No Known Activations