© 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. 87749
    Prev
    Next
    INDEX
    Explanations

    specific brands, products, and educational institutions

    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
    ishop
    -0.06
    celik
    -0.06
     hopefully
    -0.06
    esk
    -0.06
     kho
    -0.06
    hausen
    -0.06
    ÑĴ
    -0.06
    ulg
    -0.06
    arming
    -0.06
    eya
    -0.06
    POSITIVE LOGITS
     therefore
    0.08
     according
    0.07
    marshaller
    0.07
    #
    0.07
     actually
    0.07
     æķħ
    0.07
    ï¼ĮæīĢ以
    0.06
     strict
    0.06
     deÄŁil
    0.06
    /******/
    0.06
    Activations Density 0.029%

    No Known Activations