© 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. 89860
    Prev
    Next
    INDEX
    Explanations

    expressions related to making choices or selections

    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
    reu
    -0.09
    uality
    -0.08
    ycop
    -0.07
    rea
    -0.07
    yc
    -0.07
    .nz
    -0.07
    reo
    -0.07
    hcp
    -0.07
    jun
    -0.07
    oldt
    -0.07
    POSITIVE LOGITS
     wisely
    0.09
     lá»įc
    0.09
     Wis
    0.08
    eted
    0.08
    ably
    0.07
    ering
    0.07
    -made
    0.07
    ered
    0.07
    íĴĪ
    0.07
    enville
    0.07
    Activations Density 0.031%

    No Known Activations