© 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. 29353
    Prev
    Next
    INDEX
    Explanations

    features and specifications related to automotive technology

    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
    inator
    -0.06
     movers
    -0.06
     Wyn
    -0.05
    ixel
    -0.05
     Bath
    -0.05
    sit
    -0.05
     shrink
    -0.05
    self
    -0.05
     Floyd
    -0.05
    iris
    -0.05
    POSITIVE LOGITS
    ãĥ¬ãĥĥãĥĪ
    0.09
    ابÙĩ
    0.08
     Leer
    0.08
    _partitions
    0.08
    سÙĦ
    0.07
    LOCKS
    0.07
     ÑĪкÑĸ
    0.07
     car
    0.07
     беÑĢез
    0.07
    /maps
    0.07
    Activations Density 0.005%

    No Known Activations