© 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. 15633
    Prev
    Next
    INDEX
    Explanations

    references to safety standards and compliance regulations

    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
    omik
    -0.07
    بÙĪاسطة
    -0.07
     chiếc
    -0.07
    oba
    -0.06
    323
    -0.06
    _FS
    -0.06
    celik
    -0.06
    eterminate
    -0.06
    stå
    -0.06
    åł¡
    -0.06
    POSITIVE LOGITS
     industry
    0.11
     standards
    0.09
    industry
    0.08
     Industry
    0.08
     latest
    0.07
    Industry
    0.07
     international
    0.07
     Standards
    0.07
    è¡Įä¸ļ
    0.06
     relevant
    0.06
    Activations Density 0.017%

    No Known Activations