© 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. 126631
    Prev
    Next
    INDEX
    Explanations

    URLs from various domains, particularly those related to medical and governmental resources

    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
    cé
    -0.07
    lus
    -0.06
    stry
    -0.06
    olumn
    -0.06
    erdale
    -0.06
    ui
    -0.06
    iset
    -0.06
    rack
    -0.06
    igen
    -0.05
     Boeh
    -0.05
    POSITIVE LOGITS
    \widgets
    0.08
     RectTransform
    0.08
    /apps
    0.08
    omap
    0.07
    (*)(
    0.07
    allet
    0.07
    بÙĬÙĨ
    0.07
    аниÑĨ
    0.06
    blr
    0.06
    بÛĮÙĨ
    0.06
    Activations Density 0.020%

    No Known Activations