© 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. 128863
    Prev
    Next
    INDEX
    Explanations

    references to medical professionals and their communications regarding health topics

    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
    asil
    -0.07
    %A
    -0.07
    burst
    -0.07
    throp
    -0.06
     Schn
    -0.06
    &view
    -0.06
     sche
    -0.06
    Ìģc
    -0.06
    hurst
    -0.06
    .permission
    -0.06
    POSITIVE LOGITS
    indre
    0.06
     descri
    0.06
     PM
    0.06
    æ£ļ
    0.06
    agna
    0.06
    culator
    0.06
    Ä°K
    0.05
    uld
    0.05
    rire
    0.05
    /Set
    0.05
    Activations Density 0.005%

    No Known Activations