© 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. 88488
    Prev
    Next
    INDEX
    Explanations

    technical terms related to health, data, and diagnostics

    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
    äter
    -0.08
    -regexp
    -0.08
    ÙĪÙī
    -0.08
    ạm
    -0.08
    ÑĢаÑħов
    -0.08
    egas
    -0.07
    allen
    -0.07
    _launch
    -0.07
     eskort
    -0.07
     вообÑīе
    -0.07
    POSITIVE LOGITS
     thereby
    0.16
     thus
    0.14
     which
    0.12
     Thus
    0.11
     resulting
    0.11
    thus
    0.11
     hence
    0.11
     therefore
    0.10
     Consequently
    0.10
     consequently
    0.09
    Activations Density 0.125%

    No Known Activations