© 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. 17441
    Prev
    Next
    INDEX
    Explanations

    references to awards or honors related to social recognition

    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
    iales
    -0.07
    erland
    -0.07
    egie
    -0.07
    egt
    -0.07
    eworld
    -0.07
    entai
    -0.07
    loquent
    -0.07
    allax
    -0.07
    weathermap
    -0.07
    ameda
    -0.06
    POSITIVE LOGITS
     National
    0.07
    .gov
    0.07
     bic
    0.07
    quil
    0.07
    angler
    0.07
    200
    0.06
    National
    0.06
     Rum
    0.06
    th
    0.06
    ago
    0.06
    Activations Density 0.001%

    No Known Activations