© 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. 79836
    Prev
    Next
    INDEX
    Explanations

    information related to medical advice and treatment recommendations

    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
    utow
    -0.08
    bero
    -0.07
    rieve
    -0.07
    æķ¬
    -0.07
    yaw
    -0.07
    лÑİб
    -0.07
    ogi
    -0.07
    ivr
    -0.07
    uty
    -0.07
    ihan
    -0.06
    POSITIVE LOGITS
     ANT
    0.07
     resume
    0.06
     supplied
    0.06
    edom
    0.06
     swimming
    0.06
     Resume
    0.06
     ice
    0.06
    inue
    0.06
     vo
    0.06
     instructions
    0.06
    Activations Density 0.008%

    No Known Activations