© 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. 17818
    Prev
    Next
    INDEX
    Explanations

    references to sections and labeling in structured documents

    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
    IPH
    -0.07
    thing
    -0.07
    ores
    -0.07
    ogh
    -0.07
    agini
    -0.06
    ä¼´
    -0.06
     dag
    -0.06
    tero
    -0.06
    woord
    -0.06
    aç
    -0.06
    POSITIVE LOGITS
     section
    0.09
    bsd
    0.07
    section
    0.07
    _section
    0.07
    .section
    0.07
    cheduler
    0.06
    Section
    0.06
     outs
    0.06
    zeros
    0.06
    sec
    0.06
    Activations Density 0.050%

    No Known Activations