© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83997
    Prev
    Next
    INDEX
    Explanations

    events involving police encounters and arrests

    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
    ucha
    -0.08
    ãĤĩ
    -0.07
    erva
    -0.07
    throp
    -0.07
    SSIP
    -0.07
    åĢ«
    -0.07
    illard
    -0.07
    relude
    -0.07
    anou
    -0.07
    lou
    -0.07
    POSITIVE LOGITS
     arrest
    0.10
     arrested
    0.10
     arrests
    0.09
     Arrest
    0.08
     arresting
    0.08
     handc
    0.08
     Booking
    0.08
     booking
    0.07
     cuffs
    0.07
     fingerprint
    0.06
    Activations Density 0.029%

    No Known Activations