© 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. 86102
    Prev
    Next
    INDEX
    Explanations

    colloquial expressions or phrases that convey confusion or uncertainty

    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
    ":"","
    -0.06
    ses
    -0.06
    _simps
    -0.06
     hatta
    -0.06
    ÅĦ
    -0.06
    .NULL
    -0.06
     relat
    -0.06
    çĽĸ
    -0.06
     à¤īल
    -0.06
    ÑĩиÑĤ
    -0.06
    POSITIVE LOGITS
    ecome
    0.07
    awl
    0.07
    loub
    0.07
    akit
    0.07
    avanaugh
    0.07
    /Foundation
    0.07
    icari
    0.07
    morgan
    0.07
    reib
    0.07
    slaught
    0.07
    Activations Density 0.028%

    No Known Activations