© 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. 9-LLAMASCOPE-RES-131K
    11. 95754
    Prev
    Next
    INDEX
    Explanations

    elements indicative of narrative structure and significant events

    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
    ãĥ©ãĤ¹
    -0.06
    è£ľ
    -0.06
    úc
    -0.06
    deps
    -0.06
    outil
    -0.06
    UILTIN
    -0.06
    MRI
    -0.06
     sóc
    -0.06
     equipments
    -0.06
     Sesso
    -0.05
    POSITIVE LOGITS
    erdale
    0.07
    opyright
    0.07
    usb
    0.06
     íĿ¬
    0.06
    é³
    0.06
    agal
    0.06
    ``
    0.06
    /WebAPI
    0.06
    eria
    0.06
    é¬
    0.06
    Activations Density 0.000%

    No Known Activations