© 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. 29291
    Prev
    Next
    INDEX
    Explanations

    references to academic or research-related sources, particularly database links and citations

    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
    eri
    -0.07
    aepernick
    -0.07
    ubat
    -0.07
    multipart
    -0.06
    erd
    -0.06
    mare
    -0.06
    ota
    -0.06
    erald
    -0.06
    acht
    -0.06
    ucht
    -0.06
    POSITIVE LOGITS
    irs
    0.07
    æ¼ı
    0.07
    abstract
    0.06
    /renderer
    0.06
     abstract
    0.06
     Keystone
    0.06
     eius
    0.06
     AUTHOR
    0.06
    ebi
    0.06
     pornos
    0.06
    Activations Density 0.000%

    No Known Activations