© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 60347
    Prev
    Next
    INDEX
    Explanations

    references to ambitious environmental goals and innovations

    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
    ãĥ¼ãĤ¸
    -0.07
    á»ijt
    -0.07
    uren
    -0.07
     åIJĦ
    -0.07
    äºĽ
    -0.07
    биÑĤ
    -0.07
    åIJĦ
    -0.07
    pcf
    -0.07
    ắc
    -0.07
    ëĬIJ
    -0.07
    POSITIVE LOGITS
     full
    0.10
    å®Įæķ´
    0.09
     complete
    0.09
     truly
    0.08
     directly
    0.08
     whole
    0.08
     fully
    0.08
     entire
    0.08
     completely
    0.08
     direct
    0.08
    Activations Density 0.043%

    No Known Activations