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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61421
    Prev
    Next
    INDEX
    Explanations

    references to tutorials or instructional content

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

    The word "tutorial" appears in instructional content such as guides, how-to articles, navigation menus, or educational sections of websites, often referring to step-by-step instructions for learning a skill or completing a task.

    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
    guard
    -0.08
    IRC
    -0.07
    fold
    -0.07
    nen
    -0.07
    ç¼ĺ
    -0.07
    elry
    -0.07
    leigh
    -0.07
    ase
    -0.06
    alan
    -0.06
    ãģĵãĤį
    -0.06
    POSITIVE LOGITS
    tes
    0.08
    mente
    0.07
    ignon
    0.07
    weise
    0.07
    ogue
    0.07
    ship
    0.07
    ists
    0.07
    imson
    0.07
    FLASH
    0.06
    ForObject
    0.06
    Activations Density 0.007%

    No Known Activations