© 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. 106422
    Prev
    Next
    INDEX
    Explanations

    attributes related to programming or object-oriented code structure

    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
    steder
    -0.08
    skyt
    -0.07
    .builders
    -0.07
    Äįan
    -0.07
    ầm
    -0.07
    uteur
    -0.07
    icari
    -0.07
     ÑģлÑĥжби
    -0.07
    úi
    -0.07
    urb
    -0.07
    POSITIVE LOGITS
    imar
    0.07
    ived
    0.06
     eff
    0.06
    ience
    0.06
     pinch
    0.06
     cin
    0.06
    ften
    0.06
    .''↵↵
    0.05
     royal
    0.05
    *
    0.05
    Activations Density 0.000%

    No Known Activations