© 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. 74694
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions and transitional phrases that indicate combinations or contrasts in ideas

    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
    far
    -0.06
    ased
    -0.06
    Ī
    -0.06
    amate
    -0.05
    gia
    -0.05
    ewish
    -0.05
     åĺ
    -0.05
    thouse
    -0.05
    aro
    -0.05
    akte
    -0.05
    POSITIVE LOGITS
    ajas
    0.07
    hm
    0.07
    AdapterFactory
    0.07
     âĨĴ↵↵
    0.07
    zbek
    0.07
    ê¸°ë¡ľ
    0.06
    iners
    0.06
    ssid
    0.06
    SpaceItem
    0.06
    awks
    0.06
    Activations Density 0.024%

    No Known Activations