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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39288
    Prev
    Next
    INDEX
    Explanations

    keywords related to workplace safety, health hazards, and operational challenges

    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
    rape
    -0.06
     tslint
    -0.06
    ife
    -0.06
    åĪ»
    -0.05
    ABCDE
    -0.05
    ymm
    -0.05
    çĹ
    -0.05
     analog
    -0.05
    awning
    -0.05
    ritz
    -0.05
    POSITIVE LOGITS
     due
    0.14
    due
    0.12
     بسبب
    0.12
    _due
    0.12
     because
    0.11
     CAUSED
    0.11
    because
    0.11
     caused
    0.10
    åĽłä¸º
    0.10
    à¹Ģà¸ŀราะ
    0.10
    Activations Density 0.034%

    No Known Activations