© 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. 116468
    Prev
    Next
    INDEX
    Explanations

    references to time and progression in various contexts

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

    Words or phrases that introduce a clause or segment describing when something began, started, occurred, or was established.

    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
    addir
    -0.08
    imar
    -0.07
    lew
    -0.07
    iyon
    -0.07
    gid
    -0.07
    andi
    -0.06
    volt
    -0.06
    í
    -0.06
    lesi
    -0.06
    _UD
    -0.06
    POSITIVE LOGITS
     start
    0.12
     starting
    0.10
     begin
    0.10
     debut
    0.10
    éĸĭå§ĭ
    0.10
    .start
    0.10
     beginning
    0.10
    å¼Ģå§ĭ
    0.10
     starts
    0.10
     ìĭľìŀij
    0.09
    Activations Density 0.080%

    No Known Activations