© 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. 107797
    Prev
    Next
    INDEX
    Explanations

    modal verbs expressing uncertainty or obligation

    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
    ÏİÏģα
    -0.08
    еÑĢÑĭ
    -0.08
    resenter
    -0.07
     _______,
    -0.07
    à¸Ńà¸ŀ
    -0.07
    annies
    -0.07
    mans
    -0.07
    skyt
    -0.07
    neh
    -0.07
    ylon
    -0.07
    POSITIVE LOGITS
     there
    0.12
     it
    0.11
    /how
    0.09
     they
    0.08
     any
    0.07
     ever
    0.07
    there
    0.07
     perch
    0.07
     this
    0.07
     we
    0.06
    Activations Density 0.032%

    No Known Activations