© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104323
    Prev
    Next
    INDEX
    Explanations

    references to health and disease reporting

    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
    792
    -0.07
    flux
    -0.07
     ret
    -0.07
    niž
    -0.06
     Dove
    -0.06
    jur
    -0.06
    Jur
    -0.06
    etail
    -0.06
    Ìģc
    -0.06
    اذ
    -0.06
    POSITIVE LOGITS
    ogo
    0.07
    PIC
    0.06
     PIC
    0.06
    untu
    0.06
     Horizon
    0.06
    orge
    0.06
     hos
    0.06
    /animate
    0.06
     exter
    0.06
    aea
    0.06
    Activations Density 0.004%

    No Known Activations