© 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. 107934
    Prev
    Next
    INDEX
    Explanations

    phrases related to accidents and fire incidents

    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
    /tab
    -0.07
    UIL
    -0.07
    slaught
    -0.06
    AMP
    -0.06
    hawks
    -0.06
    apo
    -0.06
    uç
    -0.06
     nek
    -0.06
    ilig
    -0.06
    idel
    -0.06
    POSITIVE LOGITS
     extingu
    0.10
     fire
    0.07
     firefight
    0.07
    çģŃ
    0.07
     effectiveness
    0.07
    -cont
    0.06
     bình
    0.06
    uset
    0.06
     Fire
    0.06
    apia
    0.06
    Activations Density 0.005%

    No Known Activations