© 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. 17-LLAMASCOPE-RES-131K
    6. 129733
    Prev
    Next
    INDEX
    Explanations

    question marks and other punctuation that indicate inquiries or uncertainties

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

    Punctuation or characters that appear at line endings, often marking a transition point between different sections of text.

    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
    redient
    -0.07
    ãĥŁãĥ¥
    -0.06
    Ñĥка
    -0.06
    icals
    -0.06
    orne
    -0.06
    ilde
    -0.06
    ibar
    -0.06
    uft
    -0.06
    iffs
    -0.06
    RB
    -0.06
    POSITIVE LOGITS
     Forums
    0.08
     forums
    0.07
    Thread
    0.06
    509
    0.06
     forum
    0.06
     Thread
    0.06
     posted
    0.06
     Forum
    0.06
    ercul
    0.06
     Help
    0.06
    Activations Density 0.046%

    No Known Activations