© 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. 8607
    Prev
    Next
    INDEX
    Explanations

    first points and enumerations

    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
     also
    -0.11
     ÑĤакже
    -0.10
     ALSO
    -0.10
     Also
    -0.10
    589
    -0.10
    Also
    -0.08
    ingo
    -0.08
    assin
    -0.08
    ért
    -0.08
    also
    -0.08
    POSITIVE LOGITS
    First
    0.31
    ãģ¾ãģļ
    0.30
     first
    0.29
    é¦ĸ
    0.29
     First
    0.29
    first
    0.25
     é¦ĸ
    0.25
     primeiro
    0.23
     Firstly
    0.22
     pierws
    0.22
    Activations Density 0.163%

    No Known Activations