© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93865
    Prev
    Next
    INDEX
    Explanations

    references to integers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    side
    -0.07
    selling
    -0.07
    sing
    -0.07
     serialVersionUID
    -0.07
    ber
    -0.07
    curity
    -0.07
    anh
    -0.07
    ibur
    -0.07
     Utf
    -0.07
    ãĤį
    -0.07
    POSITIVE LOGITS
    .parseInt
    0.15
    egers
    0.08
     numberWith
    0.07
    ized
    0.07
    .MAX
    0.07
    uit
    0.07
    apolis
    0.07
    wine
    0.07
    ottes
    0.07
    ified
    0.07
    Activations Density 0.006%

    No Known Activations