© 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. 54050
    Prev
    Next
    INDEX
    Explanations

    discussions about health implications of diet and substances

    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
    ergy
    -0.07
    tearDown
    -0.06
     opioid
    -0.06
     embar
    -0.06
    iffe
    -0.06
    olute
    -0.06
    _restart
    -0.06
     ê³
    -0.06
    patient
    -0.06
     terminal
    -0.06
    POSITIVE LOGITS
    uben
    0.08
    $MESS
    0.08
     Artificial
    0.07
     sleep
    0.07
     exposure
    0.07
     artificial
    0.07
    ertz
    0.07
    çĮĽ
    0.06
    jure
    0.06
    нки
    0.06
    Activations Density 0.072%

    No Known Activations