© 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 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. 71347
    Prev
    Next
    INDEX
    Explanations

    references to museums, galleries, and art exhibits

    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
    iken
    -0.08
    ENCIL
    -0.07
    èĸ
    -0.07
    ÅĻen
    -0.06
    .decorate
    -0.06
    olini
    -0.06
    è¾°
    -0.06
    ева
    -0.06
    RAW
    -0.06
    yan
    -0.06
    POSITIVE LOGITS
     donor
    0.08
    _helpers
    0.07
     kou
    0.07
     donors
    0.07
    orex
    0.07
    /catalog
    0.06
    rita
    0.06
    805
    0.06
     attribution
    0.06
    cheon
    0.06
    Activations Density 0.002%

    No Known Activations