© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 93452
    Prev
    Next
    INDEX
    Explanations

    indicators of literary analysis or references to literary terms

    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
    ing
    -0.07
    icont
    -0.06
    mgr
    -0.06
    FFFF
    -0.06
    lat
    -0.06
    ph
    -0.06
    king
    -0.06
    สม
    -0.05
    ming
    -0.05
    Ñĸнг
    -0.05
    POSITIVE LOGITS
    /single
    0.07
    iá»ĩt
    0.07
    /Branch
    0.07
    TimeInterval
    0.07
    aren
    0.07
    .nih
    0.07
    orte
    0.07
    LayoutConstraint
    0.06
    stile
    0.06
     Verified
    0.06
    Activations Density 0.001%

    No Known Activations