© 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. 58782
    Prev
    Next
    INDEX
    Explanations

    specific numerical patterns and parameters in the data

    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
    imoto
    -0.07
     pri
    -0.06
    aken
    -0.06
    tl
    -0.06
     sides
    -0.06
    abbr
    -0.06
    chner
    -0.06
    thur
    -0.06
    hip
    -0.06
     acompan
    -0.06
    POSITIVE LOGITS
     of
    0.07
    ủa
    0.06
     amen
    0.06
    imetype
    0.06
    fram
    0.06
     tiá»ĩn
    0.06
     của
    0.06
    ãĥ©ãĤ¹
    0.06
    ë¶ĢíĦ°
    0.06
    viron
    0.06
    Activations Density 0.055%

    No Known Activations