© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74505
    Prev
    Next
    INDEX
    Explanations

    instances of destruction and impact caused by natural disasters

    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
    auer
    -0.08
    umper
    -0.08
    ump
    -0.07
    ETCH
    -0.07
    à¸²à¸ł
    -0.07
    enci
    -0.07
    æ²
    -0.07
     klu
    -0.06
    ueur
    -0.06
    _hook
    -0.06
    POSITIVE LOGITS
     wind
    0.11
     gust
    0.11
    wind
    0.10
     Wind
    0.10
    Wind
    0.09
     winds
    0.08
     Gust
    0.08
    .wind
    0.08
     Winds
    0.08
     roof
    0.07
    Activations Density 0.012%

    No Known Activations