© 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 EvalsExportsAPI 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. 29026
    Prev
    Next
    INDEX
    Explanations

    code-related terminologies and structures

    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
    azzo
    -0.07
    azzi
    -0.07
    azo
    -0.07
    olis
    -0.07
    enser
    -0.07
    rych
    -0.06
    .spotify
    -0.06
    stood
    -0.06
    $LANG
    -0.06
    estone
    -0.06
    POSITIVE LOGITS
    LError
    0.06
    671
    0.06
     Trafford
    0.06
    DownList
    0.06
    ihat
    0.06
     ÑĢок
    0.06
    ï¸
    0.06
    боÑĢ
    0.06
    FD
    0.06
    opa
    0.05
    Activations Density 0.019%

    No Known Activations