© 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. 15-LLAMASCOPE-RES-131K
    6. 26825
    Prev
    Next
    INDEX
    Explanations

    structured data or numerical representations

    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
    hu
    -0.06
    Introduced
    -0.06
     feet
    -0.06
    ohen
    -0.06
    ature
    -0.06
     DataContext
    -0.05
    ule
    -0.05
    TED
    -0.05
     mund
    -0.05
    @protocol
    -0.05
    POSITIVE LOGITS
    okit
    0.07
     etc
    0.07
    endale
    0.07
    ãĥ¼ãĥĭ
    0.07
    itzer
    0.07
    ommen
    0.07
    aeda
    0.07
    ossip
    0.07
    omik
    0.06
    antro
    0.06
    Activations Density 0.012%

    No Known Activations