© 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. 99272
    Prev
    Next
    INDEX
    Explanations

    terms indicating ease or difficulty in processes or actions

    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
    illez
    -0.07
    akes
    -0.07
     frank
    -0.07
    itchens
    -0.06
     fu
    -0.06
    ÙĤب
    -0.06
    uet
    -0.06
     once
    -0.06
    ancia
    -0.06
    ua
    -0.06
    POSITIVE LOGITS
    ôn
    0.08
     Lauderdale
    0.08
    å®ľ
    0.08
     automát
    0.07
     tabi
    0.07
     damer
    0.07
     ragazze
    0.07
    927
    0.07
    ά
    0.07
    огÑĥ
    0.07
    Activations Density 0.017%

    No Known Activations