© 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. 9721
    Prev
    Next
    INDEX
    Explanations

    <|eot_id|> followed by <|start_header_id|>user

    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
    YRO
    -0.09
     stu
    -0.09
    ENTA
    -0.09
    ledo
    -0.08
     beck
    -0.08
    cargo
    -0.08
    sko
    -0.08
     curs
    -0.08
    ached
    -0.08
     célib
    -0.08
    POSITIVE LOGITS
    <|begin_of_text|>
    0.11
    strand
    0.10
    ména
    0.09
    ì£
    0.09
    ë¨
    0.08
    rael
    0.08
    HOLDER
    0.08
    EEDED
    0.08
     Parsons
    0.08
     Term
    0.08
    Activations Density 0.097%

    No Known Activations