© 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. 118786
    Prev
    Next
    INDEX
    Explanations

    references to genetic and rare 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
    ToDevice
    -0.07
    atsby
    -0.07
    _DET
    -0.07
    tam
    -0.06
    jez
    -0.06
     Cosby
    -0.06
    asco
    -0.06
    amedi
    -0.06
    roz
    -0.06
    coli
    -0.06
    POSITIVE LOGITS
     Rare
    0.07
     rare
    0.07
     lys
    0.07
     rarity
    0.07
     Mend
    0.07
     Lump
    0.07
     autos
    0.06
    .vstack
    0.06
    lys
    0.06
     undermin
    0.06
    Activations Density 0.029%

    No Known Activations