© 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. 44674
    Prev
    Next
    INDEX
    Explanations

    final product

    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
    <|begin_of_text|>
    -0.14
    .printStackTrace
    -0.13
    nero
    -0.11
    .OnClickListener
    -0.10
    rote
    -0.09
    chaft
    -0.09
     EventArgs
    -0.09
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.09
     CURLOPT
    -0.09
     electrom
    -0.08
    POSITIVE LOGITS
    ALER
    0.10
    plib
    0.10
    ofilm
    0.09
    ForMember
    0.09
     |/
    0.08
     ãĥ¼
    0.08
    adaki
    0.08
    villa
    0.08
     recip
    0.08
    tps
    0.08
    Activations Density 0.020%

    No Known Activations