© 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. 80804
    Prev
    Next
    INDEX
    Explanations

    references to tax-related information and responsibilities

    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
     ÑħÑĥд
    -0.08
    emez
    -0.08
    (éĩij
    -0.07
    ãĥķãĥ¬
    -0.07
    obao
    -0.07
    mland
    -0.07
    omm
    -0.07
    asto
    -0.07
    ÎķÎĽ
    -0.07
    ажд
    -0.07
    POSITIVE LOGITS
    endor
    0.05
    0.05
    NSS
    0.05
     spilled
    0.05
     Fruit
    0.05
    952
    0.05
    Income
    0.05
    let
    0.05
     box
    0.05
     Income
    0.05
    Activations Density 0.045%

    No Known Activations