© 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. 3388
    Prev
    Next
    INDEX
    Explanations

    programming-related commands and syntax

    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
    alted
    -0.07
    ImageContext
    -0.07
    tember
    -0.07
    ernel
    -0.06
    æ£
    -0.06
    strup
    -0.06
     ...č↵
    -0.06
    iente
    -0.06
    awe
    -0.06
    ,...↵↵
    -0.06
    POSITIVE LOGITS
     run
    0.07
     commands
    0.07
    .run
    0.06
     Surge
    0.06
     Cyr
    0.06
     Burst
    0.06
     Industries
    0.06
    urch
    0.06
    oley
    0.05
    ãĤĤãĤĬ
    0.05
    Activations Density 0.005%

    No Known Activations