© 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. 124710
    Prev
    Next
    INDEX
    Explanations

    specific terms and descriptions related to anatomy and medical illustrations

    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
    vetica
    -0.06
     Tits
    -0.06
    azines
    -0.06
    erti
    -0.06
    ixa
    -0.06
    terra
    -0.06
    blas
    -0.06
     bail
    -0.06
    çĻĤ
    -0.06
     signature
    -0.05
    POSITIVE LOGITS
     Anatomy
    0.09
     anatomy
    0.09
     anatom
    0.09
    atomy
    0.08
     cad
    0.08
    ATOM
    0.07
     Views
    0.07
     Caj
    0.07
    èº
    0.07
    /animations
    0.06
    Activations Density 0.011%

    No Known Activations