© 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. 9-LLAMASCOPE-RES-131K
    11. 98961
    Prev
    Next
    INDEX
    Explanations

    future aspirations and desires for personal growth

    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
    arts
    -0.06
    gar
    -0.06
    ess
    -0.06
    oric
    -0.06
    iet
    -0.06
    ale
    -0.06
    iger
    -0.06
    ath
    -0.06
    essa
    -0.06
    ga
    -0.05
    POSITIVE LOGITS
    amarin
    0.09
    .scalablytyped
    0.08
    ÐIJÑĢÑħÑĸв
    0.08
    InParameter
    0.08
    /**č↵
    0.08
    GuidId
    0.08
    ekim
    0.08
    mÃŃt
    0.08
    oldur
    0.08
    bÃŃr
    0.08
    Activations Density 0.024%

    No Known Activations