© 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. 126939
    Prev
    Next
    INDEX
    Explanations

    numerical data points and their associated performance metrics in a structured format

    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
    summ
    -0.08
    ÑģÑĤа
    -0.07
    atted
    -0.07
    inch
    -0.07
    lest
    -0.06
     mere
    -0.06
     Farr
    -0.06
    /Common
    -0.06
    ta
    -0.06
    lad
    -0.06
    POSITIVE LOGITS
    saida
    0.07
    iren
    0.07
    à¥ĩ↵
    0.06
     <-
    0.06
    幸
    0.06
    endcode
    0.06
    ा↵
    0.06
    ائز
    0.06
    ovatel
    0.06
    à¥Ģ↵
    0.06
    Activations Density 0.017%

    No Known Activations