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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103984
    Prev
    Next
    INDEX
    Explanations

    terms related to neurological diseases and conditions

    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
    EDA
    -0.07
    uctose
    -0.06
    otte
    -0.06
    avic
    -0.06
     Crimes
    -0.06
    ugi
    -0.06
    -notch
    -0.06
    orts
    -0.06
    nota
    -0.06
    uty
    -0.06
    POSITIVE LOGITS
     motor
    0.08
     Motor
    0.07
     ALS
    0.07
     Carbon
    0.07
    afone
    0.07
     bul
    0.06
    motor
    0.06
     kuru
    0.06
     disability
    0.06
     carbon
    0.06
    Activations Density 0.003%

    No Known Activations