© 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. 89062
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to responses and constraints

    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
     fellow
    -0.07
    mony
    -0.07
     |_
    -0.07
    rus
    -0.07
    aign
    -0.06
    mÃŃt
    -0.06
    apy
    -0.06
     Cald
    -0.06
    ovit
    -0.06
     vice
    -0.06
    POSITIVE LOGITS
    .AutoComplete
    0.07
    ackers
    0.07
     WINAPI
    0.06
    287
    0.06
    -bearing
    0.06
     JNICALL
    0.06
    Ñıн
    0.06
    mouseleave
    0.06
    kou
    0.06
    ",{
    0.06
    Activations Density 0.048%

    No Known Activations