© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117386
    Prev
    Next
    INDEX
    Explanations

    mentions of personal health challenges and mental illness

    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
    avar
    -0.06
    γα
    -0.06
     Proto
    -0.06
     Dop
    -0.06
    illard
    -0.06
    arkin
    -0.06
    Shock
    -0.06
    ëĿ½
    -0.06
    attempt
    -0.06
    á»±c
    -0.06
    POSITIVE LOGITS
     disease
    0.09
     disability
    0.08
     condition
    0.07
    ekli
    0.07
     Disease
    0.07
    meli
    0.07
    Concurrency
    0.07
    .nih
    0.07
     diagnosis
    0.07
    bout
    0.06
    Activations Density 0.012%

    No Known Activations