© 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. 28736
    Prev
    Next
    INDEX
    Explanations

    actions related to creating or processing tasks and documents

    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
    ãĥ«ãĤ¯
    -0.07
     somehow
    -0.07
    tery
    -0.06
    isay
    -0.06
     NÄĽkter
    -0.06
    czy
    -0.06
    apor
    -0.06
    /is
    -0.06
    edin
    -0.06
     everywhere
    -0.06
    POSITIVE LOGITS
     OTHERWISE
    0.08
     ANY
    0.07
     otherwise
    0.07
    istas
    0.07
    ì´Į
    0.06
    Hall
    0.06
    gov
    0.06
    ãģ¨ãģĻãĤĭ
    0.06
    ournemouth
    0.06
    ustral
    0.06
    Activations Density 0.046%

    No Known Activations