© 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. 108803
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Peugeot" or words starting with "Pe"

    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
    ë§ī
    -0.08
    زش
    -0.07
    mos
    -0.07
    icc
    -0.07
    gli
    -0.06
     attent
    -0.06
    gmt
    -0.06
    loom
    -0.06
    ously
    -0.06
    Incoming
    -0.06
    POSITIVE LOGITS
     Pe
    0.07
    formance
    0.07
    aston
    0.07
    acock
    0.07
    Pe
    0.07
    -pe
    0.07
     pe
    0.07
    sst
    0.07
    aec
    0.07
    CAPE
    0.06
    Activations Density 0.008%

    No Known Activations