© 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. 58637
    Prev
    Next
    INDEX
    Explanations

    words starting with l

    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
    /Linux
    -0.14
    ive
    -0.12
    /loading
    -0.11
    ivet
    -0.10
    _logging
    -0.10
     luáºŃt
    -0.09
    _language
    -0.09
    /list
    -0.09
    ToLocal
    -0.09
    /lists
    -0.09
    POSITIVE LOGITS
    utenant
    0.16
    -known
    0.14
    heed
    0.14
    .parseLong
    0.13
    icrous
    0.13
    -minute
    0.13
    ening
    0.13
    ened
    0.12
    ueur
    0.12
    raries
    0.12
    Activations Density 0.307%

    No Known Activations