© 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 EvalsExportsinterp-engineNEWAPI 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. 27868
    Prev
    Next
    INDEX
    Explanations

    references to health regulations and social events

    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
    awn
    -0.07
    ikit
    -0.07
    ORIES
    -0.06
     Wrath
    -0.06
    »¿
    -0.06
    CI
    -0.06
    hawk
    -0.06
    pository
    -0.06
     è©ķ価
    -0.06
    deer
    -0.06
    POSITIVE LOGITS
    otte
    0.07
    prech
    0.06
    oga
    0.06
    ÅĽnie
    0.06
    DEX
    0.06
     Punch
    0.06
    umu
    0.06
    (æľ¨
    0.06
    arp
    0.06
    siz
    0.06
    Activations Density 0.148%

    No Known Activations