© 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. 123581
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts related to substance use disorders and mental health issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    antan
    -0.09
    ancock
    -0.08
    öl
    -0.08
    raÄį
    -0.08
    amilia
    -0.07
    ursal
    -0.07
     tròn
    -0.07
    tep
    -0.07
     Bilg
    -0.07
    echa
    -0.06
    POSITIVE LOGITS
     com
    0.07
     abuse
    0.06
     underlying
    0.06
     co
    0.06
     stim
    0.06
     conc
    0.06
     needs
    0.06
     substance
    0.06
     histories
    0.06
     medical
    0.06
    Activations Density 0.011%

    No Known Activations