© 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. 124050
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent incidents, particularly shootings and stabbings

    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
    asti
    -0.08
    ÙĪÛĮÙĩ
    -0.06
    à¥įवर
    -0.06
    andas
    -0.06
    ichert
    -0.06
    idUser
    -0.06
    á»ĵng
    -0.06
    anda
    -0.06
    озв
    -0.06
    纪
    -0.06
    POSITIVE LOGITS
    alion
    0.07
    utr
    0.07
     incident
    0.07
    itsu
    0.06
     mú
    0.06
    renal
    0.06
    ne
    0.06
    overn
    0.06
    ahy
    0.06
    car
    0.06
    Activations Density 0.018%

    No Known Activations