© 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. 54290
    Prev
    Next
    INDEX
    Explanations

    elements related to categorization and clustering of data or classifications

    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
    oldt
    -0.09
    ammen
    -0.07
    éŁ¿
    -0.06
    ommen
    -0.06
     lesb
    -0.06
    .dylib
    -0.06
    _chain
    -0.06
    Ñģим
    -0.06
    unami
    -0.06
    .cloudflare
    -0.06
    POSITIVE LOGITS
     category
    0.09
     based
    0.09
     categories
    0.09
     Category
    0.08
     Based
    0.08
    -categories
    0.08
    based
    0.07
    .categories
    0.07
     classes
    0.07
    -category
    0.07
    Activations Density 0.045%

    No Known Activations