© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76661
    Prev
    Next
    INDEX
    Explanations

    information related to natural disasters and their impacts

    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
     createSelector
    -0.07
    umo
    -0.07
     Kro
    -0.07
    roti
    -0.07
     roma
    -0.07
    rost
    -0.07
     kolo
    -0.07
    reachable
    -0.07
    unge
    -0.07
     Morse
    -0.07
    POSITIVE LOGITS
     earthquake
    0.11
     earthquakes
    0.10
     aft
    0.08
     quake
    0.08
     hypoc
    0.08
     seismic
    0.08
     fault
    0.08
     ge
    0.08
     epic
    0.07
     Earth
    0.07
    Activations Density 0.035%

    No Known Activations