© 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. 118669
    Prev
    Next
    INDEX
    Explanations

    terms related to electromagnetic radiation effects and public health concerns

    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
    anus
    -0.07
    iasm
    -0.06
     intensely
    -0.06
     اÙĦعÙħ
    -0.06
    .syntax
    -0.06
     ÑĤеÑĩ
    -0.06
    YO
    -0.06
    838
    -0.06
    /lic
    -0.06
    Resolve
    -0.06
    POSITIVE LOGITS
     harmon
    0.08
     Harmon
    0.08
     mains
    0.07
    DTD
    0.07
    ics
    0.06
    rss
    0.06
     Frequ
    0.06
     Harm
    0.06
    BAT
    0.06
     Elect
    0.06
    Activations Density 0.006%

    No Known Activations