© 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. 104901
    Prev
    Next
    INDEX
    Explanations

    phrases related to spatial organization and layering in design

    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
    çĪ½
    -0.06
     extract
    -0.06
     subs
    -0.06
    239
    -0.06
    pond
    -0.06
     Cube
    -0.06
    cube
    -0.06
     Scratch
    -0.05
     Berk
    -0.05
    esh
    -0.05
    POSITIVE LOGITS
    ãi
    0.07
    ouri
    0.07
    zier
    0.07
     cref
    0.07
    -anchor
    0.07
    å¯Ĩ
    0.07
    LEGRO
    0.07
    екаÑĢ
    0.07
    PRESS
    0.07
    éī
    0.07
    Activations Density 0.001%

    No Known Activations