© 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 EvalsExportsAPI 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. 125754
    Prev
    Next
    INDEX
    Explanations

    terminology related to legal and medical advice

    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
    езд
    -0.07
     ç¬
    -0.06
     sign
    -0.06
     Wor
    -0.06
    urg
    -0.06
    rel
    -0.06
    å¼¾
    -0.06
    971
    -0.06
    iÄĻ
    -0.06
    Ģìŀ¥
    -0.06
    POSITIVE LOGITS
     nor
    0.07
    '|
    0.07
    (always
    0.07
     advice
    0.07
    <typeof
    0.06
    lou
    0.06
    isko
    0.06
    aned
    0.06
    oen
    0.06
     Bray
    0.06
    Activations Density 0.002%

    No Known Activations