© 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. 54898
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions and analyses

    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
    esta
    -0.12
    urry
    -0.10
    ationally
    -0.09
    unal
    -0.09
    611
    -0.09
    712
    -0.09
    ãģĺ
    -0.08
    æį·
    -0.08
    MainFrame
    -0.08
    Äįel
    -0.08
    POSITIVE LOGITS
    ียà¸Ķ
    0.16
    -oriented
    0.13
     description
    0.12
    /full
    0.11
     Grat
    0.11
    -description
    0.11
    ç»Ĩ
    0.11
    sp
    0.10
     descriptions
    0.10
    /high
    0.10
    Activations Density 0.036%

    No Known Activations