© 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 EvalsExportsinterp-engineNEWAPI 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. 1768
    Prev
    Next
    INDEX
    Explanations

    expressions of agency or influence regarding actions or decisions

    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
    eba
    -0.07
    866
    -0.07
    arna
    -0.06
     Kov
    -0.06
    oba
    -0.06
    ORMAT
    -0.06
    opia
    -0.06
    ÑĢеб
    -0.06
     ones
    -0.06
    ç¨ĭ
    -0.06
    POSITIVE LOGITS
    LLL
    0.08
     nÃło
    0.08
    Uvs
    0.07
    ůr
    0.07
    olland
    0.07
    PropTypes
    0.07
    IFF
    0.07
    _fatal
    0.07
    atori
    0.06
    declspec
    0.06
    Activations Density 0.008%

    No Known Activations