© 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. 83309
    Prev
    Next
    INDEX
    Explanations

    references to evacuations and the impact of natural disasters on people's homes

    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
    avir
    -0.08
    ourg
    -0.07
    èĹ
    -0.07
    amina
    -0.07
    ivor
    -0.07
    committed
    -0.07
    habi
    -0.07
     rencont
    -0.07
    avors
    -0.06
    kills
    -0.06
    POSITIVE LOGITS
     evacuation
    0.11
     evac
    0.10
     evacuated
    0.10
     homes
    0.10
     evacuate
    0.09
    homes
    0.09
     Ev
    0.08
     Homes
    0.07
     houses
    0.06
     ev
    0.06
    Activations Density 0.005%

    No Known Activations