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. 31-LLAMASCOPE-RES-131K
    6. 43789
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and syntax

    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
    大人
    -0.07
    .Utc
    -0.07
    ekce
    -0.06
    >\<^
    -0.06
    VRT
    -0.06
    altung
    -0.06
    eda
    -0.06
    edar
    -0.06
    grund
    -0.06
    olg
    -0.06
    POSITIVE LOGITS
     linen
    0.11
     title
    0.09
    :title
    0.09
     hl
    0.09
     tab
    0.09
    ↵
    0.08
    :no
    0.08
     runnable
    0.08
    -tab
    0.07
    hl
    0.07
    Activations Density 0.006%

    No Known Activations