© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103145
    Prev
    Next
    INDEX
    Explanations

    formatting and structural elements in text

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

    Layout or navigation elements that connect different content pieces or indicate relationships between items in digital text formats.

    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
    orie
    -0.07
    uhl
    -0.06
     Bart
    -0.06
    ory
    -0.06
    bart
    -0.06
    ãĤĬãģ«
    -0.06
    oire
    -0.06
    åº
    -0.06
    gow
    -0.06
    meyi
    -0.06
    POSITIVE LOGITS
     navr
    0.07
    AndGet
    0.06
     Oyun
    0.06
    ecz
    0.06
     rodin
    0.06
    _();↵
    0.06
    urette
    0.06
    evi
    0.06
     seperate
    0.06
    imshow
    0.06
    Activations Density 0.006%

    No Known Activations