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. 43430
    Prev
    Next
    INDEX
    Explanations

    scientific notation and mathematical symbols

    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
    ç½²
    -0.06
     componentDid
    -0.06
     civilian
    -0.05
    adil
    -0.05
    SCRI
    -0.05
    _ADAPTER
    -0.05
    ayer
    -0.05
    ucene
    -0.05
     SQLITE
    -0.05
    -generator
    -0.05
    POSITIVE LOGITS
     visual
    0.09
     readability
    0.09
     text
    0.09
     visually
    0.08
     navigation
    0.08
     users
    0.08
     clickable
    0.08
     reading
    0.08
     usability
    0.08
     whitespace
    0.08
    Activations Density 0.006%

    No Known Activations