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. 44286
    Prev
    Next
    INDEX
    Explanations

    special characters and encoding issues in text

    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
     Tulsa
    -0.10
     Malaysian
    -0.10
     Kuala
    -0.09
     Malaysia
    -0.09
     Indonesia
    -0.09
     Malays
    -0.08
     Buenos
    -0.08
     Indonesian
    -0.08
     Dallas
    -0.08
     Baylor
    -0.08
    POSITIVE LOGITS
     NH
    0.23
    NH
    0.19
     Granite
    0.17
     Hampshire
    0.17
     New
    0.16
     Monad
    0.15
     Nh
    0.15
     nh
    0.14
     Vermont
    0.14
    _nh
    0.13
    Activations Density 0.003%

    No Known Activations