© 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. 119294
    Prev
    Next
    INDEX
    Explanations

    references to genetic and nutritional factors related to health

    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
    /document
    -0.08
    RootElement
    -0.07
    -animate
    -0.07
    phylum
    -0.07
    å±±å¸Ĥ
    -0.06
     franchise
    -0.06
     Skyl
    -0.06
    robat
    -0.06
    hsi
    -0.06
    หลวà¸ĩ
    -0.06
    POSITIVE LOGITS
     presence
    0.08
     polym
    0.07
    alle
    0.07
     alle
    0.07
     rs
    0.06
    presence
    0.06
    ALLEL
    0.06
    Bomb
    0.06
     Presence
    0.06
    ivery
    0.06
    Activations Density 0.006%

    No Known Activations