© 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. 86743
    Prev
    Next
    INDEX
    Explanations

    dialogue and character interactions in a script or conversation

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

    Character names or speaker identifiers at the beginning of dialogue lines in transcripts, scripts, and conversations.

    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
    elo
    -0.08
    apa
    -0.08
    Įĵ
    -0.07
    irq
    -0.07
    áy
    -0.07
    /graphql
    -0.07
    emme
    -0.07
    à¸Ļà¸Ń
    -0.07
    .nano
    -0.07
    esc
    -0.07
    POSITIVE LOGITS
    hek
    0.07
    бÑĢÑı
    0.06
    ¨
    0.05
    epam
    0.05
    UniformLocation
    0.05
    GetProcAddress
    0.05
    via
    0.05
    çݯ
    0.05
     ActionTypes
    0.05
    ku
    0.05
    Activations Density 0.009%

    No Known Activations