© 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. 70018
    Prev
    Next
    INDEX
    Explanations

    terms related to disease and medical diagnosis

    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
     Howard
    -0.07
    ?
    -0.05
     slug
    -0.05
     Brit
    -0.05
     platform
    -0.05
     parch
    -0.05
     Tar
    -0.05
     freely
    -0.05
     Crom
    -0.05
     exh
    -0.05
    POSITIVE LOGITS
    abort
    0.08
     titre
    0.08
    ivec
    0.07
     اÙĤتص
    0.07
    iros
    0.07
    åĴ
    0.07
    _firestore
    0.07
    ocol
    0.07
    .realm
    0.07
    arih
    0.07
    Activations Density 0.006%

    No Known Activations