© 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. 118721
    Prev
    Next
    INDEX
    Explanations

    closing braces and semicolons in programming syntax

    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
     Gazette
    -0.06
    BaseContext
    -0.06
    ayout
    -0.06
     Orch
    -0.06
    mini
    -0.06
    à¥įतव
    -0.06
    Calibri
    -0.06
    allis
    -0.06
     Telescope
    -0.06
     деÑĢжавного
    -0.06
    POSITIVE LOGITS
     Clayton
    0.07
    esta
    0.07
    frey
    0.06
     плаÑģÑĤи
    0.06
    LS
    0.06
    /vnd
    0.06
    ulta
    0.06
     Goodman
    0.06
     distributed
    0.06
     spre
    0.06
    Activations Density 0.004%

    No Known Activations