© 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. 47121
    Prev
    Next
    INDEX
    Explanations

    a before certain nouns

    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
     knull
    -0.09
     ži
    -0.08
    Ĥæķ°
    -0.08
    ãĥ»ãĥ»ãĥ»\n\n
    -0.08
    ErrorException
    -0.07
     geile
    -0.07
    _ioctl
    -0.07
    ãģ¡ãģ¯
    -0.07
    isory
    -0.07
    popover
    -0.07
    POSITIVE LOGITS
     ï½ľ
    0.10
    aha
    0.07
    /
    0.07
    uch
    0.06
     Progressive
    0.06
     Crosby
    0.06
     discour
    0.06
     Forbidden
    0.06
     spe
    0.06
    ahi
    0.06
    Activations Density 0.191%

    No Known Activations