© 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. 58573
    Prev
    Next
    INDEX
    Explanations

    details related to violent incidents and criminal activities

    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
    razier
    -0.07
    ÑģÑĮ
    -0.07
     gsi
    -0.07
    ıklı
    -0.07
    uilder
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    _REUSE
    -0.07
     hafta
    -0.07
    oop
    -0.06
    phem
    -0.06
    POSITIVE LOGITS
     reports
    0.07
     Initial
    0.07
     Prel
    0.06
    大人
    0.06
     initial
    0.06
    adnÃŃ
    0.06
    reports
    0.06
     preliminary
    0.06
    983
    0.06
     Reports
    0.06
    Activations Density 0.016%

    No Known Activations