© 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. 41601
    Prev
    Next
    INDEX
    Explanations

    elements related to conflict and violence

    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
     Mills
    -0.07
    389
    -0.07
     Verg
    -0.06
    into
    -0.06
    acher
    -0.06
    _iff
    -0.06
     ende
    -0.06
     into
    -0.06
     Gone
    -0.05
    ock
    -0.05
    POSITIVE LOGITS
    istine
    0.08
    íĽĪ
    0.08
    ecz
    0.07
    TRL
    0.07
    íĭ´
    0.07
    trap
    0.07
    令
    0.07
    utex
    0.07
    omit
    0.07
    unicode
    0.07
    Activations Density 0.040%

    No Known Activations