© 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. 30337
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks and statements, indicating a focus on dialogue and quoted speech

    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
     bol
    -0.07
    bol
    -0.07
    liter
    -0.07
    utz
    -0.07
    ijkstra
    -0.06
     Bol
    -0.06
    rsp
    -0.06
    ลำ
    -0.06
     Hers
    -0.06
     suppl
    -0.06
    POSITIVE LOGITS
    wyn
    0.07
    illon
    0.06
    onse
    0.06
    "While
    0.06
    827
    0.06
    ociety
    0.06
    ìĿ´ìĸ´
    0.06
    oola
    0.06
    agal
    0.06
    .metro
    0.06
    Activations Density 0.022%

    No Known Activations