© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 32810
    Prev
    Next
    INDEX
    Explanations

    <|start_header_id|>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
     invol
    -0.08
     erot
    -0.07
     lesb
    -0.07
    ,the
    -0.06
    -Russian
    -0.06
    CHASE
    -0.06
     embr
    -0.06
     \\n
    -0.06
     Richmond
    -0.06
    ihan
    -0.06
    POSITIVE LOGITS
     -*-č\n
    0.09
    <|begin_of_text|>
    0.08
    ¦æĥħ
    0.08
     salopes
    0.08
    ¶Į
    0.08
     Erotische
    0.08
    ÂĢÂĢ
    0.08
    ilogy
    0.08
    ******č\n
    0.07
     BITTE
    0.07
    Activations Density 0.490%

    No Known Activations