© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 108745
    Prev
    Next
    INDEX
    Explanations

    descriptions of texture and design in materials

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    avana
    -0.08
    arger
    -0.07
    ôi
    -0.07
    èī²çļĦ
    -0.07
    clr
    -0.06
    åĩĢ
    -0.06
     circ
    -0.06
    missive
    -0.06
    ục
    -0.06
    Äįer
    -0.06
    POSITIVE LOGITS
     texture
    0.14
     Texture
    0.14
     textures
    0.12
    Texture
    0.11
    texture
    0.11
    textures
    0.10
     surface
    0.10
     rough
    0.10
    -text
    0.10
    Textures
    0.10
    Activations Density 0.078%

    No Known Activations