© 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. 104303
    Prev
    Next
    INDEX
    Explanations

    references to authors and their works in academic citations

    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
    getJSON
    -0.07
    _lazy
    -0.06
    ãģ£ãģ¨
    -0.06
    éĤ¦
    -0.06
    Lexer
    -0.06
    _executor
    -0.06
    \modules
    -0.06
    лок
    -0.06
    çļ®
    -0.06
    agas
    -0.06
    POSITIVE LOGITS
    atory
    0.07
    림
    0.06
     conex
    0.06
    iform
    0.06
     Mou
    0.06
     Phạm
    0.06
    ãģĵãģĿ
    0.06
    ãĢĮâĢ¦âĢ¦
    0.06
    Ïģη
    0.06
    rum
    0.06
    Activations Density 0.003%

    No Known Activations