© 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. 92218
    Prev
    Next
    INDEX
    Explanations

    medical concerns related to eye health and safety

    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
    èħ¹
    -0.08
    aurus
    -0.07
    ги
    -0.07
    گاب
    -0.07
     umb
    -0.06
    estone
    -0.06
    ÑĥÑĢи
    -0.06
    γμα
    -0.06
     Gür
    -0.06
    оÑĤÑĮ
    -0.06
    POSITIVE LOGITS
     tear
    0.11
     Tears
    0.10
     Tear
    0.10
     tears
    0.09
     tearing
    0.08
     Ey
    0.07
    phthalm
    0.07
     oc
    0.07
     Lens
    0.07
     ker
    0.06
    Activations Density 0.005%

    No Known Activations