© 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 EvalsExportsinterp-engineNEWAPI 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. 61818
    Prev
    Next
    INDEX
    Explanations

    programming constructs and methods related to functionality implementation

    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
     srd
    -0.07
     actionTypes
    -0.07
     Shields
    -0.07
    /loose
    -0.06
     Rosenstein
    -0.06
    над
    -0.06
     MU
    -0.06
    isko
    -0.06
    kili
    -0.06
    cplusplus
    -0.06
    POSITIVE LOGITS
     Loved
    0.07
    ermann
    0.06
    epad
    0.06
    belt
    0.06
    isode
    0.06
    _defaults
    0.06
     Genius
    0.06
    ĸī
    0.06
    idal
    0.06
     basically
    0.06
    Activations Density 0.032%

    No Known Activations