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. 22-LLAMASCOPE-RES-131K
    6. 5605
    Prev
    Next
    INDEX
    Explanations

    HTML and file path references in the document

    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
     Heritage
    -0.06
    olor
    -0.06
     Kirk
    -0.06
     lou
    -0.05
    ores
    -0.05
     pre
    -0.05
     mat
    -0.05
     Vor
    -0.05
     Vent
    -0.05
     Kurt
    -0.05
    POSITIVE LOGITS
    afi
    0.08
    arLayout
    0.08
    agal
    0.08
    ../../../../
    0.07
    -assets
    0.07
     assets
    0.07
     ÑĦедеÑĢалÑĮ
    0.07
    ÑĮко
    0.07
    Documentation
    0.07
    oyal
    0.07
    Activations Density 0.001%

    No Known Activations