© 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. 39462
    Prev
    Next
    INDEX
    Explanations

    phrases related to incidents involving firearms or criminal activity

    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
    wheel
    -0.08
    ãģ¡ãĤĥ
    -0.07
    Multiply
    -0.07
    idot
    -0.06
    turtle
    -0.06
    agem
    -0.06
     wheel
    -0.06
    ãģĵãģ¡ãĤī
    -0.06
    |int
    -0.06
    /inc
    -0.06
    POSITIVE LOGITS
    useppe
    0.06
    ILLISECONDS
    0.06
     Approximately
    0.06
    omat
    0.06
     approximately
    0.06
    ILLISE
    0.06
    approximately
    0.06
     «
    0.06
    Approx
    0.06
    essler
    0.06
    Activations Density 0.008%

    No Known Activations