© 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. 57004
    Prev
    Next
    INDEX
    Explanations

    trends and statistics related to economics graduates and their employment

    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
    è³ŀ
    -0.08
    æĻ
    -0.06
    allax
    -0.06
    è¤
    -0.06
     Shade
    -0.06
     Shades
    -0.06
     oppon
    -0.05
    endo
    -0.05
    Hierarchy
    -0.05
     Grade
    -0.05
    POSITIVE LOGITS
     visa
    0.07
     visas
    0.07
     trend
    0.07
    pez
    0.07
    æŃ¯
    0.07
    競
    0.06
    enin
    0.06
     stream
    0.06
    gere
    0.06
    ucas
    0.06
    Activations Density 0.005%

    No Known Activations