© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 85094
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or conditions in statements

    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
     Float
    -0.07
    ÃŃž
    -0.06
     float
    -0.06
    ocio
    -0.06
     floats
    -0.06
    ungi
    -0.06
    anel
    -0.06
    451
    -0.06
     Cliff
    -0.06
    ULA
    -0.06
    POSITIVE LOGITS
    rei
    0.06
    ombok
    0.06
    aus
    0.06
    ANGLES
    0.06
    aux
    0.06
    antry
    0.06
    UMB
    0.06
    avel
    0.06
     eleg
    0.06
    йн
    0.06
    Activations Density 0.000%

    No Known Activations