© 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. 81665
    Prev
    Next
    INDEX
    Explanations

    references to genetic traits and predispositions

    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
     GetHashCode
    -0.08
    hardt
    -0.07
    èħ¾
    -0.07
     æķħ
    -0.07
    712
    -0.07
    uentes
    -0.07
     تÙĦÙģ
    -0.07
    æ¦ľ
    -0.07
    份
    -0.07
    еÑĢÑĭ
    -0.07
    POSITIVE LOGITS
     traits
    0.10
     trait
    0.09
     Mend
    0.08
     Traits
    0.08
     phen
    0.08
    traits
    0.07
     susceptibility
    0.07
     resistance
    0.07
    trait
    0.06
     phenotype
    0.06
    Activations Density 0.044%

    No Known Activations