© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29718
    Prev
    Next
    INDEX
    Explanations

    code functions, commands, and libraries

    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
    unga
    -0.10
    YLON
    -0.09
    .Åŀ
    -0.09
    abcdefghijkl
    -0.08
    Ymd
    -0.08
    otre
    -0.08
    ium
    -0.08
    atron
    -0.08
    styleType
    -0.08
     cellForRowAt
    -0.08
    POSITIVE LOGITS
     method
    0.10
     function
    0.10
     option
    0.10
     Twins
    0.08
    ede
    0.08
    ulet
    0.08
     enorm
    0.08
     command
    0.08
    riend
    0.08
    ãĥ³ãĤ°
    0.08
    Activations Density 0.023%

    No Known Activations