© 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. 63298
    Prev
    Next
    INDEX
    Explanations

    occurrences of quoted text or references

    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
    aud
    -0.07
    _XML
    -0.06
    znam
    -0.06
    .pdf
    -0.06
     genders
    -0.06
    orial
    -0.06
    camp
    -0.06
     symb
    -0.06
    @n
    -0.06
    ichel
    -0.06
    POSITIVE LOGITS
    afen
    0.06
    /Sh
    0.06
    ussy
    0.06
    물
    0.06
    usra
    0.06
    hart
    0.06
    leo
    0.06
    riad
    0.06
    /photos
    0.06
    ernes
    0.06
    Activations Density 0.001%

    No Known Activations