© 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 EvalsExportsAPI 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. 88733
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic testing and screening for diseases

    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
    arters
    -0.08
    ÑĢоÑģÑĤ
    -0.08
    estr
    -0.07
    allax
    -0.07
    Gram
    -0.07
    xCD
    -0.07
    anian
    -0.07
    ahlen
    -0.07
    ungs
    -0.07
    arter
    -0.07
    POSITIVE LOGITS
     Autos
    0.08
     autos
    0.08
     defects
    0.08
     Noon
    0.08
     gene
    0.08
     Mend
    0.08
     carrier
    0.07
     screening
    0.07
    883
    0.07
    autos
    0.07
    Activations Density 0.055%

    No Known Activations