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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4197
    Prev
    Next
    INDEX
    Explanations

    occurrences of a specific theme or subject within the text, particularly related to a central entity or idea

    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
     sobie
    -0.07
    боÑĢа
    -0.07
    oley
    -0.07
    iba
    -0.07
    EventArgs
    -0.06
    αÏģά
    -0.06
    .vertx
    -0.06
    éĸĵãģ«
    -0.06
    ös
    -0.06
    iggins
    -0.06
    POSITIVE LOGITS
     Order
    0.08
     ORDER
    0.08
     order
    0.07
    Order
    0.07
    _order
    0.07
     Orders
    0.07
    (Order
    0.07
    .Order
    0.07
    /orders
    0.07
    -order
    0.07
    Activations Density 0.002%

    No Known Activations