© 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. 16557
    Prev
    Next
    INDEX
    Explanations

    context or references to programming and code structure

    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
    ses
    -0.09
    rog
    -0.08
    fold
    -0.07
    ấm
    -0.07
    ILER
    -0.07
    weep
    -0.07
    woo
    -0.07
    UseProgram
    -0.07
    bart
    -0.06
    ÑģÑĤвоÑĢ
    -0.06
    POSITIVE LOGITS
    gether
    0.12
    antro
    0.07
    ogle
    0.07
    eniable
    0.06
    eteria
    0.06
    eriod
    0.06
    ahoma
    0.06
     STDCALL
    0.06
    etter
    0.06
    .UIManager
    0.06
    Activations Density 0.002%

    No Known Activations