© 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. 92961
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or existence of content or information

    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
    ëĶĶìĭľ
    -0.07
    stown
    -0.07
    peare
    -0.07
    ocaly
    -0.06
    .Navigator
    -0.06
    ÅĻád
    -0.06
    zell
    -0.06
    617
    -0.06
    _ASSUME
    -0.06
     Wrest
    -0.06
    POSITIVE LOGITS
    ll
    0.06
    dar
    0.06
    mit
    0.06
     sh
    0.06
    ABL
    0.05
     Lap
    0.05
    edla
    0.05
    arin
    0.05
     Kin
    0.05
     Lars
    0.05
    Activations Density 0.002%

    No Known Activations