© 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. 69907
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural markers that indicate the flow of text or conversation

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

    Sentence-ending punctuation (primarily periods) that separate related thoughts in informal personal narratives describing routines, activities or habits.

    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
    umba
    -0.07
    onna
    -0.07
     should
    -0.06
     will
    -0.06
    ushman
    -0.06
     داشت
    -0.06
    ær
    -0.06
    omik
    -0.06
    ulk
    -0.06
     was
    -0.06
    POSITIVE LOGITS
     sometimes
    0.13
    sometimes
    0.11
     Sometimes
    0.11
     occasionally
    0.10
    Sometimes
    0.10
    ometimes
    0.10
     lately
    0.09
     ocas
    0.09
     Occasionally
    0.09
     Recently
    0.09
    Activations Density 0.051%

    No Known Activations