© 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. 1421
    Prev
    Next
    INDEX
    Explanations

    temporal references related to durations and timeframes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    th
    -0.07
    st
    -0.06
     various
    -0.06
    hazi
    -0.06
     pairwise
    -0.06
    amb
    -0.06
     Berm
    -0.06
    ../../../
    -0.06
    OTO
    -0.06
    stance
    -0.06
    POSITIVE LOGITS
    -thirds
    0.14
    nd
    0.13
    /th
    0.11
    gether
    0.10
    ième
    0.09
     thirds
    0.09
     dozen
    0.09
    andal
    0.08
    -three
    0.08
     halves
    0.08
    Activations Density 0.047%

    No Known Activations