© 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. 88136
    Prev
    Next
    INDEX
    Explanations

    questions and comments related to personal evaluations and interactions

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

    Phrases representing interpersonal communication, perception, or attention directed from one person to another.

    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
    rames
    -0.07
    istributor
    -0.07
     créd
    -0.06
    styl
    -0.06
    MBOL
    -0.06
    strand
    -0.06
     precise
    -0.06
     cấp
    -0.06
    ERSION
    -0.06
     desenv
    -0.06
    POSITIVE LOGITS
     imper
    0.07
    enos
    0.06
    eday
    0.06
    wang
    0.06
     Giles
    0.06
    ior
    0.06
     Roh
    0.06
     Marin
    0.06
    mland
    0.06
     intelig
    0.06
    Activations Density 0.067%

    No Known Activations