© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 267
    Prev
    Next
    INDEX
    Explanations

    instances of interactive commands or instructions related to software or gaming

    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
    ubber
    -0.06
    erox
    -0.06
    combe
    -0.05
    orne
    -0.05
     STEP
    -0.05
    लब
    -0.05
    tej
    -0.05
    veyor
    -0.05
     inherit
    -0.05
    ...
    -0.05
    POSITIVE LOGITS
    ulp
    0.07
    uld
    0.07
    URRENCY
    0.07
     podp
    0.07
    ivatel
    0.07
    oÅĻ
    0.07
    esar
    0.07
     opak
    0.06
    ÙĪÙĦÙĬÙĪ
    0.06
    QUIT
    0.06
    Activations Density 0.001%

    No Known Activations