© 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. 86776
    Prev
    Next
    INDEX
    Explanations

    instances of phrases that indicate contrast or hesitation

    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
    Ư
    -0.07
    Styles
    -0.07
     urlpatterns
    -0.06
    ett
    -0.06
    hone
    -0.06
    cono
    -0.06
    unker
    -0.06
    заб
    -0.06
     Triumph
    -0.06
    кав
    -0.06
    POSITIVE LOGITS
    ngine
    0.08
    ãĤ¢ãĥ¼
    0.08
    heimer
    0.07
    ÑĤи
    0.07
     slightly
    0.07
     ultimately
    0.07
     also
    0.07
    ĵĺ
    0.07
    heim
    0.07
    quila
    0.07
    Activations Density 0.029%

    No Known Activations