© 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. 82836
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate actions, particularly in relation to repair, improvement, and decision-making

    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
    SizePolicy
    -0.08
     =============================================================================↵
    -0.07
    ribbon
    -0.06
    UEL
    -0.06
    ë²
    -0.06
    xec
    -0.06
    ilor
    -0.06
    =}
    -0.06
    ADATA
    -0.06
    adu
    -0.06
    POSITIVE LOGITS
    gnore
    0.07
    ÂĿ
    0.07
    bbe
    0.06
    oday
    0.06
    âĢª
    0.06
    à¸Īร
    0.06
    ivism
    0.06
    uru
    0.06
    urn
    0.06
     Matters
    0.06
    Activations Density 0.045%

    No Known Activations