© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 2368
    Prev
    Next
    INDEX
    Explanations

    elements related to textual structure and formatting

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

    Common function words and connectors that are grammatically necessary for sentence structure, particularly "the" preceding nouns and phrases like "to have" or "just" that link key components of sentences.

    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
    mouseleave
    -0.07
    cdr
    -0.07
    .club
    -0.07
    indr
    -0.06
    ennes
    -0.06
     tablesp
    -0.06
    ppv
    -0.06
    endregion
    -0.06
    677
    -0.06
    รà¸Ķ
    -0.06
    POSITIVE LOGITS
     first
    0.18
     initial
    0.17
    first
    0.15
    .first
    0.15
     start
    0.14
     early
    0.14
    -first
    0.14
    _first
    0.14
     First
    0.14
    æľĢåĪĿ
    0.14
    Activations Density 0.109%

    No Known Activations