© 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. 108691
    Prev
    Next
    INDEX
    Explanations

    unusual or unexpected occurrences and their implications

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    actively
    -0.09
    activ
    -0.08
    dest
    -0.07
    duct
    -0.07
    ä¸į足
    -0.07
    endar
    -0.07
    cord
    -0.07
    ноÑģ
    -0.07
    dee
    -0.07
    alet
    -0.07
    POSITIVE LOGITS
    sworth
    0.07
    stan
    0.07
     Myst
    0.07
    ites
    0.07
    ión
    0.07
    ecessarily
    0.07
    esco
    0.06
    IVERS
    0.06
    ertainty
    0.06
    idata
    0.06
    Activations Density 0.062%

    No Known Activations