© 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. 121547
    Prev
    Next
    INDEX
    Explanations

    symbols and syntax elements indicating errors or warnings in code

    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
    å¨ĺ
    -0.07
    ÙħÙĤ
    -0.07
    asin
    -0.07
    inx
    -0.07
    WithType
    -0.06
    pard
    -0.06
     ÑĢÑĥ
    -0.06
     skew
    -0.06
    etta
    -0.06
    aded
    -0.06
    POSITIVE LOGITS
     <--
    0.07
    728
    0.07
     <-
    0.06
    nesota
    0.06
     muse
    0.06
    ãĥ³ãĤ°ãĥ«
    0.06
    hof
    0.06
     Tanner
    0.06
     toReturn
    0.06
    rip
    0.06
    Activations Density 0.000%

    No Known Activations