© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23862
    Prev
    Next
    INDEX
    Explanations

    assistant <|end_header_id|>

    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
     gag
    -0.09
    locker
    -0.09
     Ãľl
    -0.08
    YK
    -0.08
    Locker
    -0.08
    ippers
    -0.08
     conven
    -0.08
    ayet
    -0.08
    erk
    -0.08
     useClass
    -0.08
    POSITIVE LOGITS
    ify
    0.11
    .prop
    0.09
     sve
    0.09
    们
    0.08
    atus
    0.08
    <|end_header_id|>
    0.08
    836
    0.08
    ively
    0.08
    zb
    0.08
    ä¸Ģä¸ĭ
    0.08
    Activations Density 0.218%

    No Known Activations