© 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. 9-LLAMASCOPE-RES-131K
    11. 97408
    Prev
    Next
    INDEX
    Explanations

    terms related to identification documents and cards

    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
    asse
    -0.07
    pher
    -0.06
    idden
    -0.06
    ç²¾
    -0.06
    iest
    -0.06
    ivals
    -0.06
    coma
    -0.06
    ipay
    -0.06
    irm
    -0.06
    icha
    -0.06
    POSITIVE LOGITS
    avanaugh
    0.07
     sortBy
    0.07
     parçası
    0.06
    館
    0.06
    _SI
    0.06
     Fen
    0.06
     Sting
    0.06
     Hib
    0.06
     vamp
    0.06
     khá»ıe
    0.06
    Activations Density 0.005%

    No Known Activations