© 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. 118843
    Prev
    Next
    INDEX
    Explanations

    references to visual technology and image processing in multimedia contexts

    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
     Arch
    -0.06
    зв
    -0.06
     ninh
    -0.06
     Uniform
    -0.06
    kul
    -0.06
     mass
    -0.06
     ti
    -0.05
     backlight
    -0.05
    _TOUCH
    -0.05
    :hidden
    -0.05
    POSITIVE LOGITS
     feed
    0.09
    feed
    0.09
    _feed
    0.08
     Feed
    0.08
    view
    0.08
     view
    0.07
     views
    0.07
     feeds
    0.07
    ovu
    0.07
    views
    0.07
    Activations Density 0.022%

    No Known Activations