© 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. 18677
    Prev
    Next
    INDEX
    Explanations

    first-person accounts of personal experiences or observations

    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
    alink
    -0.08
    nic
    -0.08
    ();++
    -0.08
    istine
    -0.07
    lique
    -0.07
    è²
    -0.07
    ÇIJ
    -0.07
    ãĥ«ãĤ¯
    -0.06
    isco
    -0.06
    ocs
    -0.06
    POSITIVE LOGITS
     encountered
    0.08
     encounter
    0.08
     reading
    0.07
     read
    0.07
    ehr
    0.06
     readings
    0.06
     encounters
    0.06
     gen
    0.06
    IAL
    0.06
     tried
    0.06
    Activations Density 0.017%

    No Known Activations