© 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. 108376
    Prev
    Next
    INDEX
    Explanations

    words related to confusion and lack of clarity

    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
    ughs
    -0.08
    zos
    -0.08
    \\/
    -0.07
    unya
    -0.07
    tak
    -0.07
    _NUMERIC
    -0.07
     Wy
    -0.07
    lify
    -0.07
    رÙĪز
    -0.07
    chu
    -0.07
    POSITIVE LOGITS
    /conf
    0.13
     confusion
    0.08
     confuse
    0.08
    ingly
    0.07
     conf
    0.07
     confusing
    0.07
     Conf
    0.07
     about
    0.07
     confused
    0.07
    Å¡t
    0.07
    Activations Density 0.009%

    No Known Activations