© 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. 128686
    Prev
    Next
    INDEX
    Explanations

    HTML document structure elements

    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
    kit
    -0.07
    Toolkit
    -0.06
    ॰
    -0.06
    oodles
    -0.06
    MOVED
    -0.06
    692
    -0.06
    ends
    -0.06
    .hl
    -0.06
    òi
    -0.06
    emmel
    -0.06
    POSITIVE LOGITS
     Bien
    0.07
    atile
    0.07
    ;charset
    0.07
    istring
    0.06
    UTF
    0.06
    getManager
    0.06
    upported
    0.06
    obia
    0.06
    aby
    0.06
    memberOf
    0.06
    Activations Density 0.001%

    No Known Activations