© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78095
    Prev
    Next
    INDEX
    Explanations

    terms related to inflammation and its characteristics

    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
     yet
    -0.07
    atoria
    -0.06
     Kane
    -0.06
     once
    -0.06
    tek
    -0.06
    ä¸Ģ
    -0.06
     her
    -0.06
     vic
    -0.06
    [
    -0.06
    ÂŃ
    -0.05
    POSITIVE LOGITS
    /renderer
    0.10
     kostenlose
    0.09
    abwe
    0.09
    ÃŃÅ¡
    0.08
     proport
    0.08
    ãĤ¤ãĤº
    0.08
    .onView
    0.08
    conde
    0.08
    ÑĤÑĢо
    0.08
    -addons
    0.08
    Activations Density 0.001%

    No Known Activations