© 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. 42712
    Prev
    Next
    INDEX
    Explanations

    references to music charts and rankings

    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
    ses
    -0.08
    elman
    -0.07
     Seznam
    -0.07
    azor
    -0.07
    orado
    -0.06
     à¹Ĩ
    -0.06
    rench
    -0.06
    pty
    -0.06
    atar
    -0.06
    siz
    -0.06
    POSITIVE LOGITS
    .gov
    0.10
    .com
    0.08
    ÃĴ
    0.07
    .org
    0.07
    :index
    0.07
     ÐłÐ¤
    0.07
    iards
    0.07
    trs
    0.07
    Ž
    0.07
    èĪŀ
    0.07
    Activations Density 0.002%

    No Known Activations