© 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. 92527
    Prev
    Next
    INDEX
    Explanations

    function declarations and prototypes in a programming context

    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
    gili
    -0.08
    voje
    -0.07
    culus
    -0.07
    stdafx
    -0.07
    ugo
    -0.06
    .Normalize
    -0.06
    ahkan
    -0.06
    rin
    -0.06
     AppBundle
    -0.06
    rá
    -0.06
    POSITIVE LOGITS
     Praha
    0.06
    292
    0.06
    cker
    0.06
    302
    0.06
    ether
    0.06
    аÑĤа
    0.06
    obic
    0.06
    -Smith
    0.06
    \Bundle
    0.05
    ixels
    0.05
    Activations Density 0.015%

    No Known Activations