© 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. 58237
    Prev
    Next
    INDEX
    Explanations

    concepts related to uncertainty in scientific models and outcomes

    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
    subtype
    -0.06
    imli
    -0.06
    arte
    -0.06
    æĸ¹æ¡Ī
    -0.06
    /shared
    -0.06
     mapping
    -0.06
     pou
    -0.06
    arl
    -0.06
     poss
    -0.06
     releg
    -0.06
    POSITIVE LOGITS
     measures
    0.14
     metrics
    0.13
     Measures
    0.13
     measure
    0.13
     variables
    0.12
    metrics
    0.12
    measure
    0.11
     Measure
    0.11
     metric
    0.11
     medidas
    0.11
    Activations Density 0.223%

    No Known Activations