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. 43549
    Prev
    Next
    INDEX
    Explanations

    visual representations or descriptors related to monuments and sculptures

    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
     '_
    -0.07
     '
    -0.07
     '--
    -0.07
     '[
    -0.07
     '**
    -0.07
     Organisation
    -0.07
     '..
    -0.07
     '#
    -0.07
    olson
    -0.06
     realise
    -0.06
    POSITIVE LOGITS
     XV
    0.08
     vys
    0.07
     XVI
    0.07
     allegedly
    0.07
     XII
    0.07
     XIV
    0.07
     knight
    0.06
     XIII
    0.06
     vy
    0.06
     knights
    0.06
    Activations Density 0.012%

    No Known Activations