© 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. 80206
    Prev
    Next
    INDEX
    Explanations

    terms related to medical diagnoses and treatment efficacy, particularly for urinary tract infections and related conditions

    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
     sple
    -0.07
     tumor
    -0.07
     sore
    -0.06
    ÑĢоÑģÑĤ
    -0.06
    upo
    -0.06
     silver
    -0.05
    гал
    -0.05
    коÑĤ
    -0.05
    ucch
    -0.05
     Minority
    -0.05
    POSITIVE LOGITS
     cases
    0.08
    ãĥ¼ãĥĵ
    0.08
    cases
    0.08
     Cases
    0.07
    åĪĿ
    0.07
    /inet
    0.07
    Ñīи
    0.07
    Cases
    0.07
    oud
    0.07
    atte
    0.07
    Activations Density 0.047%

    No Known Activations