© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53958
    Prev
    Next
    INDEX
    Explanations

    indicators of additional information or requests for more details

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ullo
    -0.07
    rong
    -0.07
    pdo
    -0.07
    atoire
    -0.06
    qli
    -0.06
     Scar
    -0.06
     ============================================================================↵
    -0.06
    ÑıÑħ
    -0.06
    _ASSUME
    -0.06
    égorie
    -0.06
    POSITIVE LOGITS
     Goldberg
    0.07
    िड
    0.06
     Moor
    0.06
    icc
    0.06
     Carroll
    0.06
     Pager
    0.06
    yny
    0.06
    ellig
    0.06
     Fluid
    0.06
     fluid
    0.05
    Activations Density 0.002%

    No Known Activations