© 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. 86835
    Prev
    Next
    INDEX
    Explanations

    instances of violent actions and related physical attributes

    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
    esteem
    -0.07
    arta
    -0.07
    виÑī
    -0.06
    arnation
    -0.06
     hypnot
    -0.06
    commons
    -0.06
    stry
    -0.06
    .getElementsByName
    -0.06
    asca
    -0.06
    schema
    -0.06
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.10
     wherever
    0.09
     anywhere
    0.09
     location
    0.08
    åľ°çĤ¹
    0.08
     tại
    0.08
     near
    0.08
    Anywhere
    0.07
    location
    0.07
     Outside
    0.07
    Activations Density 0.114%

    No Known Activations