© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 86879
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and expressions related to statistical concepts

    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
    onica
    -0.07
    _probability
    -0.07
    inery
    -0.07
    celik
    -0.07
    oundary
    -0.07
    swana
    -0.07
    agal
    -0.07
    arshal
    -0.07
    erdale
    -0.07
     Haut
    -0.06
    POSITIVE LOGITS
     mean
    0.17
     Mean
    0.15
     average
    0.15
    mean
    0.15
    .mean
    0.15
    average
    0.14
    Mean
    0.14
     averages
    0.13
     Average
    0.13
    å¹³åĿĩ
    0.13
    Activations Density 0.142%

    No Known Activations