© 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. 76608
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to form inputs in HTML

    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
    alar
    -0.07
     Ùħراج
    -0.06
    olta
    -0.06
    aes
    -0.06
    usal
    -0.06
    nite
    -0.06
    halt
    -0.06
    Ø´Ùħ
    -0.06
    èm
    -0.06
    -pay
    -0.06
    POSITIVE LOGITS
     search
    0.15
     Search
    0.13
    search
    0.12
     searching
    0.12
    Search
    0.11
    .search
    0.11
    -search
    0.11
     searches
    0.11
    .Search
    0.11
    æIJľç´¢
    0.11
    Activations Density 0.011%

    No Known Activations