© 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. 71309
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    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
    iedy
    -0.07
    ogue
    -0.07
    меÑĤÑĮ
    -0.07
    .WinForms
    -0.07
    /preferences
    -0.07
    ullo
    -0.07
    è·Ł
    -0.07
    åŁĭ
    -0.06
    urd
    -0.06
    haft
    -0.06
    POSITIVE LOGITS
    elop
    0.07
     addCriterion
    0.07
    427
    0.06
    793
    0.06
    422
    0.06
    els
    0.06
    ت
    0.06
    atoria
    0.06
    79
    0.06
    rips
    0.06
    Activations Density 0.054%

    No Known Activations