© 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. 31583
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or sentence breaks in the 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
    Æ¡
    -0.07
     ashes
    -0.06
     Zaman
    -0.06
    xfff
    -0.06
    füg
    -0.06
    екÑģÑĥ
    -0.06
    ÑĢÑĥÑĩ
    -0.06
     Polynomial
    -0.06
    nds
    -0.06
    à¸ļาย
    -0.06
    POSITIVE LOGITS
     or
    0.08
     and
    0.08
    ainer
    0.07
    ienes
    0.06
    idla
    0.06
    ope
    0.05
    uÃŃ
    0.05
    (equalTo
    0.05
     Dread
    0.05
    ลล
    0.05
    Activations Density 0.009%

    No Known Activations