© 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. 104972
    Prev
    Next
    INDEX
    Explanations

    references to structural organization within documentation

    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
    unger
    -0.07
    umbo
    -0.07
    abay
    -0.07
    noinspection
    -0.07
     Graves
    -0.06
    alog
    -0.06
    gett
    -0.06
     grav
    -0.06
    _uart
    -0.06
    maz
    -0.06
    POSITIVE LOGITS
     section
    0.06
    trak
    0.06
     resultMap
    0.06
    .section
    0.06
    eldorf
    0.06
    -section
    0.06
    section
    0.06
     sections
    0.06
     Section
    0.06
     Hast
    0.05
    Activations Density 0.001%

    No Known Activations