© 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. 107012
    Prev
    Next
    INDEX
    Explanations

    references to controversial or problematic media content

    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
     Egyptian
    -0.07
     Egypt
    -0.07
    ocommerce
    -0.07
     spiders
    -0.07
    @js
    -0.06
     Cairo
    -0.06
     snakes
    -0.06
    ubes
    -0.06
    issan
    -0.06
    ICODE
    -0.06
    POSITIVE LOGITS
    spa
    0.08
     Clamp
    0.07
     Horton
    0.07
    ÄĻk
    0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.07
    olle
    0.06
     Lor
    0.06
     вÑģ
    0.06
    oreal
    0.06
    opol
    0.06
    Activations Density 0.003%

    No Known Activations