© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 62835
    Prev
    Next
    INDEX
    Explanations

    references to sports previews and analysis

    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
     Richards
    -0.07
    isay
    -0.06
    หล
    -0.06
    à¹ģà¸Ļ
    -0.06
    away
    -0.06
    öy
    -0.06
    rox
    -0.06
     Duplicate
    -0.06
    sted
    -0.06
     Extract
    -0.06
    POSITIVE LOGITS
     coverage
    0.07
    ellas
    0.07
    ableObject
    0.07
    _exempt
    0.07
    OTA
    0.07
    antly
    0.07
     //</
    0.07
    ascending
    0.06
    Cover
    0.06
    iano
    0.06
    Activations Density 0.019%

    No Known Activations