© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89084
    Prev
    Next
    INDEX
    Explanations

    indicators of approval ratings or public opinion statistics

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

    Embedded tweets within articles or documents, where the text immediately follows a tweet that has been quoted. The delimiter marks the transition from a tweet to the continuation of the main article 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
    reon
    -0.08
    одÑĥ
    -0.07
    ingleton
    -0.07
    rier
    -0.07
    лаÑģÑĤи
    -0.07
    pesan
    -0.07
    berra
    -0.07
    åĬ¨çĶŁæĪIJ
    -0.07
    нами
    -0.07
    ãĥ¡ãĥªãĤ«
    -0.07
    POSITIVE LOGITS
     noqa
    0.06
    0.06
     coax
    0.05
    θι
    0.05
    pong
    0.05
     sorte
    0.05
    oman
    0.05
     rooft
    0.05
     straw
    0.05
    _relu
    0.05
    Activations Density 0.003%

    No Known Activations