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. 43906
    Prev
    Next
    INDEX
    Explanations

    discussions about artistic independence and the balance between art and commerce

    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
    _Customer
    -0.06
    -describedby
    -0.06
    emics
    -0.06
    çī¹èī²
    -0.06
    人åı£
    -0.06
    å·§
    -0.06
     patriotism
    -0.06
    eken
    -0.06
    specialchars
    -0.05
    _EMIT
    -0.05
    POSITIVE LOGITS
     studio
    0.14
    studio
    0.12
     studios
    0.11
    Studio
    0.11
     Studio
    0.11
     painting
    0.10
     plein
    0.09
     practice
    0.09
     Painting
    0.09
     process
    0.09
    Activations Density 0.112%

    No Known Activations