© 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. 86443
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and dialogue interactions

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

    Opening words of direct speech or dialogue, especially featuring introductory phrases, personal pronouns, greetings, or speaker identification.

    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
    hots
    -0.06
    åĽŀæĿ¥
    -0.06
    owie
    -0.06
    acter
    -0.06
    byterian
    -0.06
    rescia
    -0.06
    GLOBALS
    -0.06
    lamaz
    -0.06
    enal
    -0.06
    hiba
    -0.06
    POSITIVE LOGITS
     sir
    0.07
     Sir
    0.07
    æ·
    0.06
    emen
    0.06
    argon
    0.06
     Dove
    0.06
    .onDestroy
    0.06
     searching
    0.06
     Tou
    0.06
     Tic
    0.06
    Activations Density 0.022%

    No Known Activations