© 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. 38307
    Prev
    Next
    INDEX
    Explanations

    collective expressions of gratitude and appreciation

    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
    bidden
    -0.07
    plits
    -0.07
    estation
    -0.06
    ightly
    -0.06
    ruz
    -0.06
    aname
    -0.06
    aub
    -0.06
    ìŀĸ
    -0.06
     poz
    -0.06
    pare
    -0.06
    POSITIVE LOGITS
     your
    0.08
    appa
    0.07
     yours
    0.07
    imm
    0.06
    ogi
    0.06
    adius
    0.06
    ä½łçļĦ
    0.06
    475
    0.06
    906
    0.06
     appreciate
    0.06
    Activations Density 0.027%

    No Known Activations