© 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. 1168
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and names, particularly related to Plymouth and Dwight D. Eisenhower

    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
    ing
    -0.08
    Ùij
    -0.07
    ingt
    -0.07
    steen
    -0.07
    sets
    -0.07
    uyo
    -0.07
    sembly
    -0.07
    ξη
    -0.07
    ley
    -0.07
    posables
    -0.07
    POSITIVE LOGITS
    .gdx
    0.09
    oord
    0.07
    opper
    0.07
    ../../
    0.07
    athan
    0.07
    eenth
    0.06
    .habbo
    0.06
    istrovstvÃŃ
    0.06
    erras
    0.06
    .pretty
    0.06
    Activations Density 0.034%

    No Known Activations