© 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 EvalsExportsAPI 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. 3537
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wait" and related phrases indicating anticipation or pause

    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
    ysters
    -0.07
    ζε
    -0.07
    istributor
    -0.07
    RIA
    -0.07
    qus
    -0.07
    ÅĻel
    -0.06
    blo
    -0.06
    enu
    -0.06
    adolu
    -0.06
    nock
    -0.06
    POSITIVE LOGITS
    .Serial
    0.06
    ĻĤ
    0.06
    ancel
    0.06
    -breaking
    0.06
    949
    0.06
     -------------------------------------------------------------------------
    0.05
    å¾ħ
    0.05
    iolet
    0.05
    ebek
    0.05
    ings
    0.05
    Activations Density 0.003%

    No Known Activations