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

    Neuronpedia

    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. 105652
    Prev
    Next
    INDEX
    Explanations

    terms related to gun violence and associated research issues

    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
     Fist
    -0.07
    unread
    -0.07
    .nasa
    -0.07
    ÅĻet
    -0.06
    intel
    -0.06
    ãĥ¼ãĥģ
    -0.06
    uiten
    -0.06
    á»ĭ
    -0.06
    nger
    -0.06
     relief
    -0.06
    POSITIVE LOGITS
     Ak
    0.07
    -peer
    0.07
     Granite
    0.06
    ModelError
    0.06
     violence
    0.06
     Violence
    0.06
     дÑĥ
    0.06
    stown
    0.06
     ventil
    0.06
    åł´
    0.06
    Activations Density 0.009%

    No Known Activations