© 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. 58654
    Prev
    Next
    INDEX
    Explanations

    instances of physical violence and abuse

    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
    undler
    -0.08
     ÎļαÏĦηγοÏģία
    -0.07
    licer
    -0.07
    792
    -0.07
    inki
    -0.07
     trùng
    -0.07
    idget
    -0.07
    isse
    -0.07
    ÑĢÑıдÑĥ
    -0.07
     bordel
    -0.07
    POSITIVE LOGITS
     beat
    0.07
     fit
    0.07
    Ìģc
    0.06
    odÄĽ
    0.06
    beat
    0.06
    íĪ¬
    0.06
     beaten
    0.05
     leading
    0.05
     d
    0.05
     RT
    0.05
    Activations Density 0.012%

    No Known Activations