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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88587
    Prev
    Next
    INDEX
    Explanations

    references to web development practices and user interface components

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

    The token sequence frequently appears at sentence or clause boundaries, often marking grammatical transitions like conjunctions ("but", "so", "and") or sentence-starting elements. These transitions typically precede explanatory content or introduce new information that elaborates on previous statements.

    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
    uÄį
    -0.07
     подв
    -0.07
    наÑĩе
    -0.07
    å¯Ħ
    -0.06
     зов
    -0.06
    ãģıãģł
    -0.06
     jež
    -0.06
    寸
    -0.06
    تÙħ
    -0.06
    èĬĿ
    -0.06
    POSITIVE LOGITS
     sometimes
    0.10
     often
    0.08
    sometimes
    0.08
    ambi
    0.08
     Sometimes
    0.07
    often
    0.07
    ometimes
    0.07
    Sometimes
    0.07
    วà¸Ļ
    0.07
     frequently
    0.06
    Activations Density 0.086%

    No Known Activations