© 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 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. 119322
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to emergency response and medical scenarios

    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
    ORIZ
    -0.08
    hev
    -0.07
    rek
    -0.07
     navigator
    -0.07
    icha
    -0.07
    ritel
    -0.07
    cycle
    -0.07
    atto
    -0.07
    /REC
    -0.07
    952
    -0.07
    POSITIVE LOGITS
     mobil
    0.06
    uest
    0.06
     drills
    0.06
     during
    0.06
    ass
    0.06
    assets
    0.06
     shelter
    0.05
    quarter
    0.05
     surviv
    0.05
     Shelter
    0.05
    Activations Density 0.014%

    No Known Activations