© 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. 76768
    Prev
    Next
    INDEX
    Explanations

    indicators of significant events or trends in legislation and societal changes

    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
     Lew
    -0.07
    arming
    -0.06
    -fw
    -0.06
    ä»ĬæĹ¥
    -0.06
    lest
    -0.06
    ole
    -0.06
    otti
    -0.06
     hôm
    -0.06
    inema
    -0.06
    Merit
    -0.06
    POSITIVE LOGITS
     Year
    0.09
    å¹´
    0.09
     год
    0.09
     year
    0.09
    Year
    0.08
    .year
    0.08
    année
    0.08
     ÑĢÑĸк
    0.08
    ëħĦ
    0.07
     годÑĥ
    0.07
    Activations Density 0.014%

    No Known Activations