© 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. 8623
    Prev
    Next
    INDEX
    Explanations

    code syntax snippets

    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
    SENT
    -0.08
    unu
    -0.08
    ijn
    -0.08
     Tender
    -0.08
    232
    -0.08
    ane
    -0.08
    irst
    -0.08
    .SQLException
    -0.08
     Dana
    -0.08
     Spar
    -0.08
    POSITIVE LOGITS
    <|begin_of_text|>
    0.11
    _tokenize
    0.11
    asca
    0.10
    ï½Ĭ
    0.09
    //**\n
    0.08
    AndGet
    0.08
    celik
    0.08
    ĵn
    0.08
    lied
    0.08
    ERSHEY
    0.08
    Activations Density 0.075%

    No Known Activations