© 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. 16489
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Dale

    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
    üb
    -0.07
    ráž
    -0.06
    ÑĮко
    -0.06
    estar
    -0.06
    ãĥĥãĤ¯
    -0.06
    rated
    -0.06
    iated
    -0.06
    rega
    -0.06
    inely
    -0.06
    doors
    -0.06
    POSITIVE LOGITS
    y
    0.09
    alto
    0.08
    igh
    0.08
    yw
    0.07
     Carnegie
    0.07
    wood
    0.06
    ล
    0.06
     Shr
    0.06
    оди
    0.06
    spl
    0.06
    Activations Density 0.001%

    No Known Activations