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. 43470
    Prev
    Next
    INDEX
    Explanations

    title elements and indicators of authorship in documents

    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
     doc
    -0.07
     exact
    -0.06
     Counts
    -0.06
     customer
    -0.06
     simply
    -0.06
     congr
    -0.06
     pair
    -0.06
    áºŃu
    -0.06
     precision
    -0.05
     cle
    -0.05
    POSITIVE LOGITS
    Narrated
    0.10
    Contrib
    0.10
    Illustr
    0.10
    Designed
    0.10
    Compiled
    0.10
    Editor
    0.10
    Artist
    0.09
     Illustrator
    0.09
    Designer
    0.09
    Introduction
    0.09
    Activations Density 0.008%

    No Known Activations