© 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. 5271
    Prev
    Next
    INDEX
    Explanations

    discussions about woodworking techniques and tools

    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
    #
    -0.08
    brick
    -0.08
    gard
    -0.08
    èĽĽ
    -0.07
     welded
    -0.07
     Grass
    -0.07
     welding
    -0.07
    éĵ
    -0.07
     sew
    -0.07
    wire
    -0.07
    POSITIVE LOGITS
     wood
    0.16
     timber
    0.14
    æľ¨
    0.14
    wood
    0.13
     gá»Ĺ
    0.13
     wooden
    0.12
     Wood
    0.12
     hardwood
    0.12
    Wood
    0.12
     Wooden
    0.12
    Activations Density 0.124%

    No Known Activations