© 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 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. 87985
    Prev
    Next
    INDEX
    Explanations

    references to current events and related topics in news articles

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

    Double quotation marks around article titles in citation formats, often followed by publication names and dates.

    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
    оÑĢони
    -0.08
    _PHP
    -0.07
    /inet
    -0.07
     Picker
    -0.07
     addCriterion
    -0.07
    vangst
    -0.07
     Pick
    -0.06
    ÙĬÙĦا
    -0.06
     ä½ı
    -0.06
     Thrones
    -0.06
    POSITIVE LOGITS
     How
    0.09
     Why
    0.08
    kel
    0.07
    atem
    0.07
     understanding
    0.06
     Lessons
    0.06
    How
    0.06
     entitled
    0.06
     Does
    0.06
     Unsigned
    0.06
    Activations Density 0.218%

    No Known Activations