© 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. 53719
    Prev
    Next
    INDEX
    Explanations

    details related to symptoms and effects of a specific medical condition

    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
    iw
    -0.06
    oral
    -0.06
     brain
    -0.06
    ullan
    -0.06
    znik
    -0.06
     ro
    -0.06
     Gut
    -0.06
     Next
    -0.06
    á»ĵng
    -0.06
     ye
    -0.06
    POSITIVE LOGITS
    rame
    0.07
    ç¾½
    0.06
     sitting
    0.06
    ìķħ
    0.06
     Tradable
    0.06
     touched
    0.06
    inges
    0.06
    Ùħد
    0.06
     Spoon
    0.06
    oyal
    0.06
    Activations Density 0.010%

    No Known Activations