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. 43616
    Prev
    Next
    INDEX
    Explanations

    references to related topics or articles

    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
    anko
    -0.08
    SCRIPTION
    -0.06
    ãĥ¬ãĥ¼
    -0.06
    ampo
    -0.06
    anner
    -0.06
    agle
    -0.06
    ProgressHUD
    -0.06
     respective
    -0.06
    анÑĭ
    -0.06
    apes
    -0.06
    POSITIVE LOGITS
     Topics
    0.15
     Items
    0.14
    ly
    0.13
     topics
    0.11
     Topic
    0.11
     Subjects
    0.11
     Searches
    0.11
     Links
    0.11
     Item
    0.10
     tags
    0.10
    Activations Density 0.005%

    No Known Activations