© 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. 89137
    Prev
    Next
    INDEX
    Explanations

    code snippets and variable assignments related to data structures or programming functions

    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
    isor
    -0.08
    antan
    -0.07
    ibraltar
    -0.07
    obs
    -0.07
     XPAR
    -0.06
    dbuf
    -0.06
    arak
    -0.06
    azer
    -0.06
    genes
    -0.06
    ÏĦι
    -0.06
    POSITIVE LOGITS
     intern
    0.06
    NewItem
    0.06
     equip
    0.06
    جاد
    0.06
    uby
    0.06
     Equip
    0.06
    .Module
    0.06
     Lage
    0.06
    éĹ²
    0.06
    داÙħ
    0.06
    Activations Density 0.017%

    No Known Activations