© 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. 14765
    Prev
    Next
    INDEX
    Explanations

    instances of conversational fillers and expressions of 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
    AGMA
    -0.08
    ukes
    -0.08
     consect
    -0.07
    rect
    -0.07
    qv
    -0.07
    imi
    -0.07
    ORS
    -0.07
    ellen
    -0.07
    ihat
    -0.07
    que
    -0.07
    POSITIVE LOGITS
    -minded
    0.12
     minded
    0.12
     Minds
    0.07
    íĥľ
    0.06
    OLUMN
    0.06
     figure
    0.05
     @"\
    0.05
    PNG
    0.05
     Cyr
    0.05
    anh
    0.05
    Activations Density 0.018%

    No Known Activations