© 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. 15-LLAMASCOPE-RES-131K
    11. 87347
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a quantity or magnitude

    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
    né
    -0.07
    CELER
    -0.07
    _verbose
    -0.06
    eldorf
    -0.06
    aries
    -0.06
    ainen
    -0.06
    alink
    -0.06
    elen
    -0.06
    arkin
    -0.06
    urious
    -0.06
    POSITIVE LOGITS
    .updateDynamic
    0.07
     Portions
    0.07
    ucher
    0.06
    engu
    0.06
    erville
    0.06
    867
    0.06
    idian
    0.06
    _Load
    0.06
     âĶĥ
    0.06
    oby
    0.06
    Activations Density 0.000%

    No Known Activations