© 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. 91535
    Prev
    Next
    INDEX
    Explanations

    numerical values or specific data points in a document

    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
    oya
    -0.08
    aney
    -0.08
    TING
    -0.07
    ompson
    -0.07
    æ´²
    -0.07
    coming
    -0.07
    ing
    -0.07
    anj
    -0.06
    turned
    -0.06
    asley
    -0.06
    POSITIVE LOGITS
    folio
    0.09
    WEEN
    0.07
    onz
    0.07
     latter
    0.07
    ess
    0.07
    à¥įà¤ł
    0.07
    issance
    0.07
    ween
    0.07
    ously
    0.07
    ellan
    0.07
    Activations Density 0.026%

    No Known Activations