© 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. 117269
    Prev
    Next
    INDEX
    Explanations

    references to teamwork and problem-solving in historical contexts

    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
    è¡Ĺ
    -0.07
    .integration
    -0.06
     LSB
    -0.06
    kits
    -0.06
    azo
    -0.06
     KBS
    -0.06
    ius
    -0.06
    ighborhood
    -0.06
    usto
    -0.06
    #
    -0.06
    POSITIVE LOGITS
     survival
    0.09
     Survival
    0.08
     stranded
    0.07
     Lone
    0.07
     lone
    0.07
    Surv
    0.07
    /browse
    0.06
    isol
    0.06
    \Persistence
    0.06
     scientific
    0.06
    Activations Density 0.001%

    No Known Activations