© 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. 58421
    Prev
    Next
    INDEX
    Explanations

    topics related to genetics and reproductive technologies

    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
    ekim
    -0.08
    itzer
    -0.08
    mouth
    -0.07
    hoc
    -0.07
    ndl
    -0.07
    jde
    -0.07
    ynet
    -0.07
    ãģĸ
    -0.07
    orque
    -0.07
    iggers
    -0.07
    POSITIVE LOGITS
     carrier
    0.07
     gene
    0.06
     carriers
    0.06
     Mend
    0.06
     Tay
    0.06
     repair
    0.06
     targeted
    0.06
     carried
    0.06
     Huntington
    0.06
     target
    0.06
    Activations Density 0.015%

    No Known Activations