© 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. 15-LLAMASCOPE-RES-131K
    6. 27161
    Prev
    Next
    INDEX
    Explanations

    patterns or elements related to publishing dates, titles, and links in written content

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

    Section breaks or delimiters in web content that typically appear at transitions between content elements like dates, titles, categories, or author information.

    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
    ãĥ¬ãĥ¼
    -0.07
    isman
    -0.06
    pok
    -0.06
    mando
    -0.06
    çIJ
    -0.06
    overy
    -0.06
     grace
    -0.06
    Ngh
    -0.06
    ìĬµ
    -0.06
    梯
    -0.06
    POSITIVE LOGITS
    .ToolTip
    0.06
    elves
    0.06
     forn
    0.06
    tember
    0.06
    pps
    0.06
    ksi
    0.06
    ä¸Ģèά
    0.06
    xffffffff
    0.06
     outlet
    0.06
     Woo
    0.06
    Activations Density 0.022%

    No Known Activations