© 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. 2965
    Prev
    Next
    INDEX
    Explanations

    instances of the word "text" and its related terms in coding contexts

    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
    theless
    -0.07
     clipped
    -0.07
    ationToken
    -0.07
    thon
    -0.07
    lation
    -0.07
    alty
    -0.07
    ment
    -0.07
    ok
    -0.07
    ry
    -0.07
    /dis
    -0.06
    POSITIVE LOGITS
    ually
    0.12
    MeshPro
    0.10
    ual
    0.09
    -decoration
    0.09
    ImageRelation
    0.08
    /plain
    0.08
    uring
    0.08
    icular
    0.08
    uality
    0.08
    .RegularExpressions
    0.08
    Activations Density 0.065%

    No Known Activations