© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90075
    Prev
    Next
    INDEX
    Explanations

    culinary instructions and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Common functional words found in instructional text, particularly action verbs, relational terms, and operational descriptors in procedural contexts like recipes, sports reporting, and career guidance.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    /or
    -0.08
    -turned
    -0.06
    .omg
    -0.06
    het
    -0.06
    apter
    -0.06
    AMED
    -0.06
     ‘
    -0.06
     InitializeComponent
    -0.05
    .EventArgs
    -0.05
    梨
    -0.05
    POSITIVE LOGITS
     veter
    0.09
    $MESS
    0.09
    âĹİ
    0.08
    айд
    0.08
     Ãľl
    0.07
    Ngh
    0.07
    âĸ²
    0.07
    :\/\/
    0.07
    ÑĸÑĪ
    0.07
    tÄĽÅ¾
    0.07
    Activations Density 0.404%

    No Known Activations