© 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. 15-LLAMASCOPE-RES-131K
    11. 21
    Prev
    Next
    INDEX
    Explanations

    references to violent events and related terminology

    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
    ÏĢλα
    -0.07
    ouple
    -0.07
     Guerr
    -0.07
    lick
    -0.06
    avr
    -0.06
    oir
    -0.06
    arkin
    -0.06
    erva
    -0.06
    $instance
    -0.06
    UBLE
    -0.06
    POSITIVE LOGITS
    å¯¾å¿ľ
    0.07
    odash
    0.07
     heck
    0.06
    त
    0.06
     вÑĩ
    0.06
     Heritage
    0.06
    kinson
    0.06
     Kirst
    0.05
    vu
    0.05
     geil
    0.05
    Activations Density 0.004%

    No Known Activations