© 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. 108955
    Prev
    Next
    INDEX
    Explanations

    references to the word "which."

    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
    ủa
    -0.07
    ney
    -0.07
    ivel
    -0.06
    acco
    -0.06
    '.$
    -0.06
    ávÄĽ
    -0.06
     genie
    -0.06
    ìī
    -0.06
    rone
    -0.06
     annonce
    -0.06
    POSITIVE LOGITS
    ilton
    0.08
    ften
    0.07
     many
    0.07
    many
    0.06
     there
    0.06
     we
    0.06
     proudly
    0.06
    ulton
    0.06
    ¥
    0.06
    ilere
    0.06
    Activations Density 0.006%

    No Known Activations