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. 44355
    Prev
    Next
    INDEX
    Explanations

    image file formats, specifically JPEG and GIF

    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
    Ð®ÐĽ
    -0.06
    úsqueda
    -0.06
    ëį°ìĿ´íĬ¸
    -0.06
     Gupta
    -0.06
    avic
    -0.06
    ayload
    -0.06
     female
    -0.05
    hausen
    -0.05
    ÑĸмÑĸ
    -0.05
    arius
    -0.05
    POSITIVE LOGITS
    .pages
    0.11
    ?v
    0.10
    ?t
    0.09
    .opt
    0.09
    &w
    0.09
    .gallery
    0.09
    .jpeg
    0.09
    .web
    0.08
    -large
    0.08
    ?id
    0.07
    Activations Density 0.010%

    No Known Activations