© 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. 15-LLAMASCOPE-RES-131K
    11. 87828
    Prev
    Next
    INDEX
    Explanations

    terms related to structure, organization, and systematic processes

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

    Nouns or technical terms that appear at sentence or paragraph boundaries in diverse content sources, often in contexts that suggest automated content aggregation or translation.

    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
    adu
    -0.07
     же
    -0.07
    ascript
    -0.07
    æ¡
    -0.07
    asel
    -0.07
    aq
    -0.07
    ÄĻż
    -0.06
    iddet
    -0.06
    едини
    -0.06
    .Spring
    -0.06
    POSITIVE LOGITS
    lessly
    0.07
    707
    0.06
     Mind
    0.06
    ocs
    0.06
    sthrough
    0.06
    itaire
    0.06
    Connell
    0.06
    typeid
    0.06
    IMARY
    0.06
    675
    0.06
    Activations Density 0.003%

    No Known Activations