© 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. 22075
    Prev
    Next
    INDEX
    Explanations

    `opens` and `file` following `my` or `store`

    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
    eva
    -0.10
    RuleContext
    -0.09
    .jpg
    -0.09
    ev
    -0.09
    ya
    -0.08
    ActionCode
    -0.08
    DbType
    -0.08
    ilia
    -0.08
    .expect
    -0.08
     Julian
    -0.08
    POSITIVE LOGITS
     extends
    0.12
    .Companion
    0.10
    /*@
    0.09
     heightFor
    0.09
    ongsTo
    0.09
    ycastle
    0.08
    printStats
    0.08
    าà¸ĩว
    0.08
    atten
    0.08
    pData
    0.08
    Activations Density 0.093%

    No Known Activations