© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61586
    Prev
    Next
    INDEX
    Explanations

    references to significant individuals or groups in a context that highlights their influence or actions

    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
     Arte
    -0.06
    æĪĴ
    -0.06
     Asp
    -0.06
    iversit
    -0.06
    inte
    -0.06
    aker
    -0.05
    óc
    -0.05
    jur
    -0.05
    atisfaction
    -0.05
     Lux
    -0.05
    POSITIVE LOGITS
     migrationBuilder
    0.08
    .scalablytyped
    0.07
     addCriterion
    0.07
    åłĤ
    0.07
     Tire
    0.07
    ToSelector
    0.07
    abcdefghijkl
    0.07
     Slug
    0.07
    imin
    0.07
    Toe
    0.07
    Activations Density 0.000%

    No Known Activations