© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127227
    Prev
    Next
    INDEX
    Explanations

    elements related to layout and visual design in a user interface

    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
     rating
    -0.06
    arian
    -0.06
    æķħ
    -0.06
    overlay
    -0.06
    log
    -0.06
    essions
    -0.06
     oily
    -0.05
    ville
    -0.05
     danh
    -0.05
    _MODIFIED
    -0.05
    POSITIVE LOGITS
     appearance
    0.09
    ppe
    0.07
     Fior
    0.07
     appearances
    0.07
     appear
    0.07
    waukee
    0.07
    лÑİÑĩа
    0.07
    ODEV
    0.07
     STDMETHODCALLTYPE
    0.07
    bourne
    0.07
    Activations Density 0.017%

    No Known Activations