© 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. 93140
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential or possibility in various contexts

    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
    strup
    -0.07
    ấp
    -0.07
    à¥įड
    -0.07
    رÛĮز
    -0.07
     sanki
    -0.07
    .PL
    -0.07
    Ñģим
    -0.07
    usa
    -0.07
    å¹
    -0.06
    owi
    -0.06
    POSITIVE LOGITS
     even
    0.10
     could
    0.07
     also
    0.07
    /pro
    0.07
     sogar
    0.07
    even
    0.07
    anges
    0.07
     quite
    0.06
     hundreds
    0.06
    haps
    0.06
    Activations Density 0.010%

    No Known Activations