© 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. 121559
    Prev
    Next
    INDEX
    Explanations

    concepts related to health and community advocacy

    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
    etty
    -0.08
    _sensitive
    -0.07
    Statics
    -0.07
    iggs
    -0.07
    bole
    -0.07
    YTE
    -0.07
    hton
    -0.07
    preter
    -0.07
    phies
    -0.07
    ileaks
    -0.07
    POSITIVE LOGITS
     meas
    0.06
     civ
    0.06
     res
    0.06
     Dob
    0.06
     coached
    0.05
     Marketplace
    0.05
     since
    0.05
     gal
    0.05
    Tracker
    0.05
    oved
    0.05
    Activations Density 0.026%

    No Known Activations