© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17525
    Prev
    Next
    INDEX
    Explanations

    instances of the word "at" used as a preposition indicating time or location

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     weir
    -0.06
     Herz
    -0.06
    Bid
    -0.06
    çľī
    -0.06
     Bid
    -0.06
    ylland
    -0.06
    ìĿ´ìĬ¤
    -0.06
     kos
    -0.06
     noble
    -0.06
     Day
    -0.06
    POSITIVE LOGITS
    umont
    0.08
    eneg
    0.07
    vetica
    0.07
    .btnClose
    0.07
    tero
    0.07
     Bris
    0.06
    itech
    0.06
    Lua
    0.06
    nton
    0.06
    azen
    0.06
    Activations Density 0.001%

    No Known Activations