© 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. 17-LLAMASCOPE-RES-131K
    11. 71280
    Prev
    Next
    INDEX
    Explanations

    specific terms and names related to various industries, especially in technology and culture

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

    Foreign language words or word fragments embedded within English text, particularly from Germanic, Romance, and other European languages.

    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
    itt
    -0.07
    Sharper
    -0.07
    ITT
    -0.07
    eson
    -0.07
    aec
    -0.07
    aucoup
    -0.06
    ackbar
    -0.06
    psc
    -0.06
    ityEngine
    -0.06
    croft
    -0.06
    POSITIVE LOGITS
    entimes
    0.07
    lename
    0.07
    Ñīее
    0.06
    elijk
    0.06
    ÅĽci
    0.06
     aliqua
    0.06
    bih
    0.06
    kening
    0.06
    ordinate
    0.06
     Loy
    0.06
    Activations Density 0.080%

    No Known Activations