© 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. 79607
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to running programs or scripts

    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
    aus
    -0.06
     fro
    -0.06
    -devel
    -0.06
     Leather
    -0.06
     Vill
    -0.06
     æ¤
    -0.06
    baugh
    -0.06
     mirror
    -0.06
     norge
    -0.06
     Solid
    -0.06
    POSITIVE LOGITS
     run
    0.11
    run
    0.10
     ./
    0.10
    .run
    0.10
    "./
    0.09
    (run
    0.09
    /run
    0.09
     runs
    0.09
    -run
    0.09
    _run
    0.09
    Activations Density 0.033%

    No Known Activations