© 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. 92475
    Prev
    Next
    INDEX
    Explanations

    technical references to software development frameworks and tools

    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
    .scalablytyped
    -0.09
    ewis
    -0.08
    klad
    -0.07
    esh
    -0.07
    stream
    -0.06
    geois
    -0.06
    ãģ¨ãģĵãĤį
    -0.06
    elry
    -0.06
    ÑģÑı
    -0.06
    ertas
    -0.06
    POSITIVE LOGITS
    .Forms
    0.07
    rink
    0.07
    ÑĨÑı
    0.07
    -made
    0.06
    .intellij
    0.06
    isation
    0.06
    udev
    0.06
     Wheeler
    0.06
    paged
    0.06
    _placement
    0.06
    Activations Density 0.000%

    No Known Activations