© 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. 30230
    Prev
    Next
    INDEX
    Explanations

    phrases related to links or connections

    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
    PTION
    -0.06
    strap
    -0.06
     compost
    -0.06
    ãĥªãĥ¼
    -0.06
    zar
    -0.06
    ç«Ł
    -0.06
    ÄIJT
    -0.06
    zim
    -0.06
    覧
    -0.06
     rehab
    -0.06
    POSITIVE LOGITS
    olland
    0.07
    ekt
    0.06
    ö
    0.06
    pire
    0.06
    edin
    0.06
    лей
    0.06
    ining
    0.06
     Typ
    0.06
    enef
    0.06
    istencia
    0.06
    Activations Density 0.003%

    No Known Activations