© 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. 107637
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and disorders

    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
     indeed
    -0.07
    Indeed
    -0.06
     therein
    -0.06
     notamment
    -0.06
     zem
    -0.06
    aving
    -0.06
     Indeed
    -0.06
    umat
    -0.06
    度
    -0.06
    elerik
    -0.06
    POSITIVE LOGITS
     is
    0.09
     similarly
    0.08
    }elseif
    0.08
     ëĬĶ
    0.07
     meanwhile
    0.07
     likewise
    0.07
    hausen
    0.07
     adalah
    0.07
     merupakan
    0.07
     isa
    0.07
    Activations Density 0.032%

    No Known Activations