© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119456
    Prev
    Next
    INDEX
    Explanations

    keywords related to environmental health hazards, particularly those associated with wireless radiation, toxins, and plastic pollution

    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
    nder
    -0.07
    diamond
    -0.07
    523
    -0.06
    gems
    -0.06
    enser
    -0.06
    peater
    -0.06
     strtol
    -0.06
    engan
    -0.06
    aal
    -0.06
    atron
    -0.06
    POSITIVE LOGITS
    ursal
    0.07
     present
    0.07
    /colors
    0.07
    -containing
    0.07
    eden
    0.07
    çŃij
    0.07
    зÑĭ
    0.06
     içeren
    0.06
    zet
    0.06
    iveness
    0.06
    Activations Density 0.027%

    No Known Activations