© 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. 14113
    Prev
    Next
    INDEX
    Explanations

    quotations or dialogues within the text

    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
    AGO
    -0.06
    .untracked
    -0.06
    .ActionBar
    -0.06
     Wikip
    -0.06
    /apps
    -0.06
    ục
    -0.06
    avo
    -0.06
    å¼ķãģį
    -0.06
    arch
    -0.06
    -Sah
    -0.06
    POSITIVE LOGITS
     Leer
    0.08
    ĩĮ
    0.06
    èĪĪ
    0.06
    elaide
    0.06
    ideo
    0.06
    ersions
    0.06
    utzer
    0.06
    icker
    0.06
    usion
    0.06
     Meaning
    0.06
    Activations Density 0.020%

    No Known Activations