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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93702
    Prev
    Next
    INDEX
    Explanations

    commands and actions related to programming or terminal usage

    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
    vely
    -0.08
    hus
    -0.08
    illac
    -0.07
    ario
    -0.07
    arters
    -0.07
    bstract
    -0.07
    alet
    -0.06
    anitize
    -0.06
    udeau
    -0.06
    .CV
    -0.06
    POSITIVE LOGITS
     commands
    0.10
    åij½ä»¤
    0.09
     command
    0.09
     Commands
    0.08
     åij
    0.08
     команд
    0.07
    commands
    0.07
    -command
    0.07
     commanded
    0.07
    command
    0.07
    Activations Density 0.008%

    No Known Activations