© 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. 128772
    Prev
    Next
    INDEX
    Explanations

    key elements and significant details related to artistic or cultural events

    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
    ãĥ³ãĤ¯
    -0.07
    ietet
    -0.07
    ั
    -0.06
    еле
    -0.06
    verse
    -0.06
    маз
    -0.06
    lbrace
    -0.06
     Pompe
    -0.06
    nothrow
    -0.06
    ÙĪات
    -0.06
    POSITIVE LOGITS
    宽
    0.07
     Chips
    0.06
     organic
    0.06
     ÑĪи
    0.06
    _featured
    0.06
    amam
    0.06
    -dat
    0.06
     width
    0.06
    asio
    0.06
    inema
    0.06
    Activations Density 0.002%

    No Known Activations