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. 43819
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols related to specific mathematical or technical notations

    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
     recon
    -0.06
     reconstruction
    -0.06
    rise
    -0.05
     cl
    -0.05
    leitung
    -0.05
    ãĥIJãĥ¼
    -0.05
     tit
    -0.05
     engineer
    -0.05
     antic
    -0.05
    ertain
    -0.05
    POSITIVE LOGITS
     Wishlist
    0.08
     wishlist
    0.08
     wish
    0.07
    ingroup
    0.07
     quantity
    0.07
     qty
    0.07
    osu
    0.07
    subpackage
    0.07
    oux
    0.07
    _quantity
    0.07
    Activations Density 0.003%

    No Known Activations