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. 5779
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and structure, particularly in code comments and function definitions

    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
     Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł Âł
    -0.07
    rella
    -0.07
     enim
    -0.07
    erial
    -0.07
    â̦â̦â̦â̦â̦â̦â̦â̦â̦â̦â̦â̦â̦â̦â̦â̦
    -0.06
    aves
    -0.06
    heim
    -0.06
     PRIMARY
    -0.06
    ava
    -0.06
    lum
    -0.06
    POSITIVE LOGITS
     Buna
    0.07
    ãĥĬãĥ«
    0.07
    addtogroup
    0.06
     Liv
    0.06
    ecko
    0.06
    misc
    0.06
     âĺ
    0.06
    ÃŃstica
    0.06
    nels
    0.06
    kea
    0.06
    Activations Density 0.003%

    No Known Activations