© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42553
    Prev
    Next
    INDEX
    Explanations

    segments or sections of text that include quotations or references

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Double angle brackets (">>") appearing at the end of structured content like lists, tables, or organized information, often marking where the content ends before transitioning to new material.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    lias
    -0.07
    از
    -0.07
    ýt
    -0.07
    _________________↵↵
    -0.07
    athi
    -0.06
    еÐ
    -0.06
    izon
    -0.06
    liÄŁinin
    -0.06
    ÑģÑĤа
    -0.06
    idor
    -0.06
    POSITIVE LOGITS
    -LAST
    0.07
     NÄĽkterá
    0.06
     Alv
    0.06
    /INFO
    0.06
     Lud
    0.06
    aira
    0.06
    ieux
    0.06
    _mex
    0.06
    allen
    0.06
     respectively
    0.06
    Activations Density 0.049%

    No Known Activations