© 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. 54449
    Prev
    Next
    INDEX
    Explanations

    statements regarding the nature and limitations of medical content or 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
    Ļ¨
    -0.07
    ç¦
    -0.07
     Ott
    -0.07
    éĻµ
    -0.06
     consenting
    -0.06
     Dos
    -0.06
    ÑİÑĢ
    -0.06
    ëłĪìĬ¤
    -0.06
    Ø´ÙĪ
    -0.06
    /close
    -0.06
    POSITIVE LOGITS
    odom
    0.07
     Portal
    0.07
    ources
    0.07
    ĩ
    0.06
     inaccur
    0.06
     Pages
    0.06
     stale
    0.06
    зÑĮ
    0.06
     error
    0.06
    Portal
    0.06
    Activations Density 0.007%

    No Known Activations