© 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. 81673
    Prev
    Next
    INDEX
    Explanations

    alphanumeric codes or identifiers

    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
    avors
    -0.07
    ijkstra
    -0.07
     Gren
    -0.07
    odem
    -0.07
    510
    -0.07
    increments
    -0.07
    lop
    -0.07
    rightness
    -0.06
    uteur
    -0.06
    isu
    -0.06
    POSITIVE LOGITS
    Amazon
    0.07
     Amazon
    0.07
    amazon
    0.06
    iteur
    0.06
    let
    0.06
     lean
    0.06
     dyst
    0.06
     Throne
    0.06
     amazon
    0.06
     Nail
    0.06
    Activations Density 0.002%

    No Known Activations