© 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. 15-LLAMASCOPE-RES-131K
    11. 27057
    Prev
    Next
    INDEX
    Explanations

    references to legislative committees and their activities

    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
    éIJ
    -0.07
    .FontStyle
    -0.07
    åŃĺäºİ
    -0.06
    ichten
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    гÑĥ
    -0.06
    ToDate
    -0.06
    ichtet
    -0.06
    æ°ĹæĮģãģ¡
    -0.06
    ified
    -0.06
    POSITIVE LOGITS
    lan
    0.07
     leadership
    0.07
    zig
    0.07
    phis
    0.06
     Bair
    0.06
     chá»Ŀ
    0.06
    bay
    0.06
    rin
    0.06
    Accessory
    0.06
    biz
    0.06
    Activations Density 0.022%

    No Known Activations