© 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. 17-LLAMASCOPE-RES-131K
    11. 81465
    Prev
    Next
    INDEX
    Explanations

    references to various roles and relationships in team dynamics

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

    Common formatting, structural, or connecting elements in text, particularly in bibliographic references, HTML code, or document organization.

    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
    ĥ
    -0.08
    ety
    -0.08
    UMB
    -0.08
    enheim
    -0.08
    umba
    -0.08
    ulumi
    -0.07
    ackbar
    -0.07
    okit
    -0.07
    coli
    -0.07
    psilon
    -0.07
    POSITIVE LOGITS
    ients
    0.06
     Chủ
    0.06
    venir
    0.05
     sooner
    0.05
     server
    0.05
     him
    0.05
    erman
    0.05
    ¤
    0.05
    aser
    0.05
    /
    0.05
    Activations Density 0.143%

    No Known Activations