© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83737
    Prev
    Next
    INDEX
    Explanations

    instances of code closure and structure, particularly brackets and 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
     resc
    -0.06
    gerald
    -0.06
     desk
    -0.06
    HeaderView
    -0.06
     Weiner
    -0.06
    coni
    -0.06
    uty
    -0.06
     бÑİджеÑĤ
    -0.06
    pler
    -0.06
     con
    -0.06
    POSITIVE LOGITS
    za
    0.06
     Affero
    0.06
    _lastname
    0.06
    igar
    0.06
    zure
    0.06
    uto
    0.06
    agar
    0.06
    amil
    0.06
    egrator
    0.06
     etc
    0.06
    Activations Density 0.010%

    No Known Activations