© 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. 96211
    Prev
    Next
    INDEX
    Explanations

    expressions of interest or fascination in various topics

    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
    oli
    -0.08
    urge
    -0.06
    ffa
    -0.06
    alem
    -0.06
    zin
    -0.06
    Ñİк
    -0.06
    cid
    -0.06
    ä¹ĭä¸Ģ
    -0.06
    =@"
    -0.06
    ages
    -0.06
    POSITIVE LOGITS
    Å¡em
    0.08
    -looking
    0.07
    ysize
    0.07
     about
    0.07
    tright
    0.06
     situ
    0.06
    commons
    0.06
    cipher
    0.06
    tring
    0.06
    Ïĥη
    0.06
    Activations Density 0.008%

    No Known Activations