© 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. 73282
    Prev
    Next
    INDEX
    Explanations

    words related to violent incidents and accidents

    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
    iscard
    -0.07
    stell
    -0.07
    stem
    -0.06
    ates
    -0.06
    ëĬ
    -0.06
     beled
    -0.06
     Dumpster
    -0.06
    igest
    -0.06
     guilty
    -0.06
    hz
    -0.06
    POSITIVE LOGITS
     involving
    0.12
     happening
    0.07
     case
    0.07
    sis
    0.07
    993
    0.07
    0.06
     involve
    0.06
     involves
    0.06
     happened
    0.06
     occurring
    0.06
    Activations Density 0.017%

    No Known Activations