© 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. 70079
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "buzz" and its variations, indicating popularity or excitement

    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
    ennen
    -0.08
    ately
    -0.07
    halb
    -0.07
    ennon
    -0.06
    ergus
    -0.06
    itaire
    -0.06
    ctal
    -0.06
    ãĤ¶ãĥ¼
    -0.06
    uring
    -0.06
    ussen
    -0.06
    POSITIVE LOGITS
    feed
    0.08
    iness
    0.07
    Buzz
    0.07
    buz
    0.07
    Feed
    0.07
     buzz
    0.07
     Karlov
    0.07
    amil
    0.07
    INESS
    0.06
    ypi
    0.06
    Activations Density 0.006%

    No Known Activations