© 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. 125681
    Prev
    Next
    INDEX
    Explanations

    topics related to illegal waste disposal and environmental issues

    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
    ervo
    -0.07
     Shade
    -0.06
     disaster
    -0.06
    TEGER
    -0.06
     Cz
    -0.06
     colour
    -0.06
    enti
    -0.06
     firing
    -0.06
     US
    -0.06
    ansi
    -0.06
    POSITIVE LOGITS
    åĨĬ
    0.07
    836
    0.07
    ajaran
    0.06
    Ïģγ
    0.06
     behaviors
    0.06
    .rd
    0.06
    ì¸ł
    0.06
    /stats
    0.06
    elry
    0.06
    -*-
    0.06
    Activations Density 0.005%

    No Known Activations