© 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. 98127
    Prev
    Next
    INDEX
    Explanations

    navigational elements in text

    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
    akh
    -0.06
    гл
    -0.06
    $MESS
    -0.06
    rink
    -0.06
    ÑıÑĩ
    -0.06
    oped
    -0.06
    γα
    -0.06
    etail
    -0.05
    lescope
    -0.05
    venture
    -0.05
    POSITIVE LOGITS
    attered
    0.07
    elson
    0.07
     GANG
    0.07
    izu
    0.06
     cocos
    0.06
    èĩ
    0.06
     modelName
    0.06
    abcdefghijkl
    0.06
    ienes
    0.06
    IEW
    0.06
    Activations Density 0.003%

    No Known Activations