© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40700
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript functions related to manipulating the DOM

    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
    asi
    -0.08
    chio
    -0.07
    .nano
    -0.06
    кÑĥл
    -0.06
    ãĥ¥ãĥ¼
    -0.06
    isay
    -0.06
    .relative
    -0.06
    rome
    -0.06
    nu
    -0.06
    leans
    -0.06
    POSITIVE LOGITS
    à¸ļาย
    0.07
     Herr
    0.06
    CLUDING
    0.06
    piler
    0.06
    icated
    0.06
    OffsetTable
    0.06
    FormattedMessage
    0.05
    uled
    0.05
    oÄŁ
    0.05
    ERRU
    0.05
    Activations Density 0.003%

    No Known Activations