© 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. 16359
    Prev
    Next
    INDEX
    Explanations

    family-related content

    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
    /DTD
    -0.07
    urga
    -0.07
    wyn
    -0.06
     Wonderland
    -0.06
    least
    -0.06
    ew
    -0.06
    owski
    -0.06
    umbing
    -0.06
    oga
    -0.06
    иÑĤ
    -0.06
    POSITIVE LOGITS
    896
    0.07
    overe
    0.06
     Racing
    0.06
     adult
    0.06
     grown
    0.06
     paren
    0.06
    442
    0.06
    55
    0.06
     raised
    0.06
     RET
    0.06
    Activations Density 0.014%

    No Known Activations