© 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 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. 61046
    Prev
    Next
    INDEX
    Explanations

    actions related to physical altercations and confrontations

    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
    entes
    -0.08
    ecta
    -0.07
    AuthProvider
    -0.07
    reon
    -0.07
    mlin
    -0.07
    aidu
    -0.06
    ÑĢÑĥ
    -0.06
    rijk
    -0.06
    iras
    -0.06
    endon
    -0.06
    POSITIVE LOGITS
     struggle
    0.07
     Ingram
    0.06
     struggling
    0.06
    anel
    0.06
     struggles
    0.06
     hy
    0.06
     Dickens
    0.06
     Daniel
    0.06
     struggled
    0.06
    ocos
    0.06
    Activations Density 0.007%

    No Known Activations