© 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. 9-LLAMASCOPE-RES-131K
    11. 97786
    Prev
    Next
    INDEX
    Explanations

    terms related to gastrointestinal diseases

    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
    plan
    -0.06
     acknow
    -0.06
    jam
    -0.06
     neck
    -0.05
     Vend
    -0.05
    anye
    -0.05
    emy
    -0.05
     bod
    -0.05
     bot
    -0.05
     Hunt
    -0.05
    POSITIVE LOGITS
    dez
    0.07
    urst
    0.07
    orne
    0.07
    eron
    0.07
    /loose
    0.07
     McKin
    0.07
    даÑĤ
    0.07
    ãĤ·ãĥ¼
    0.07
    IRST
    0.07
    Å¡Å¥
    0.07
    Activations Density 0.002%

    No Known Activations