© 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. 29095
    Prev
    Next
    INDEX
    Explanations

    terms related to uncertainty and its impact on modeling

    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
    emoth
    -0.07
    644
    -0.06
     Stanton
    -0.06
    pz
    -0.06
    osg
    -0.06
    oya
    -0.06
    uche
    -0.06
    _lit
    -0.06
    avors
    -0.06
    à¸
    -0.06
    POSITIVE LOGITS
     corrupt
    0.07
    PERT
    0.07
    NSError
    0.07
     random
    0.07
     uncertainty
    0.07
     uncertain
    0.07
     systematic
    0.07
     error
    0.07
    Random
    0.07
     Trab
    0.07
    Activations Density 0.081%

    No Known Activations