© 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. 28499
    Prev
    Next
    INDEX
    Explanations

    instances of opening and closing brackets in code structures

    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
    οÏį
    -0.07
    translator
    -0.06
     ste
    -0.06
    uo
    -0.06
    YE
    -0.06
     м
    -0.06
     Harr
    -0.06
    /build
    -0.06
     cez
    -0.06
    =rand
    -0.06
    POSITIVE LOGITS
     case
    0.08
     cases
    0.08
    Case
    0.08
    oon
    0.08
     casos
    0.07
     Brom
    0.07
    cases
    0.07
     CASE
    0.07
    CASE
    0.07
    -case
    0.07
    Activations Density 0.010%

    No Known Activations