Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5467
    Prev
    Next
    INDEX
    Explanations

    references to coding conventions and functions in programming

    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
    .appspot
    -0.07
    uuml
    -0.06
     cocks
    -0.06
     Nimbus
    -0.06
     jer
    -0.06
    /perl
    -0.06
    ãĥ¼ãĥŃ
    -0.06
     Abrams
    -0.06
    ope
    -0.06
    outh
    -0.06
    POSITIVE LOGITS
    cwd
    0.09
     cwd
    0.08
     AST
    0.07
    erna
    0.07
     pkg
    0.07
    koa
    0.07
    quirer
    0.07
    pkg
    0.07
     bail
    0.06
     glob
    0.06
    Activations Density 0.009%

    No Known Activations