© 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. 76422
    Prev
    Next
    INDEX
    Explanations

    instances of JavaScript and AngularJS syntax or code structure

    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
    ahat
    -0.07
    %C
    -0.07
    StackSize
    -0.07
    PILE
    -0.07
    usher
    -0.06
    cente
    -0.06
    baum
    -0.06
    .jav
    -0.06
    fty
    -0.06
    ovid
    -0.06
    POSITIVE LOGITS
    747
    0.06
    929
    0.06
    360
    0.06
    325
    0.06
    cal
    0.06
    GetInstance
    0.06
    xA
    0.06
    Spe
    0.06
    327
    0.06
     Locker
    0.06
    Activations Density 0.004%

    No Known Activations