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. 44012
    Prev
    Next
    INDEX
    Explanations

    concepts relating to data analysis and predictive modeling

    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
    arnation
    -0.06
    .dds
    -0.06
    	Copyright
    -0.06
    ipmap
    -0.06
    æĴ®
    -0.06
    Collision
    -0.06
    abyrinth
    -0.06
     нав
    -0.06
    DataExchange
    -0.06
     Morg
    -0.06
    POSITIVE LOGITS
     sentiment
    0.17
     Sent
    0.14
     polarity
    0.14
     sentiments
    0.13
     sentimental
    0.13
    Sent
    0.12
     tweet
    0.12
    sent
    0.11
     SENT
    0.11
    _sent
    0.11
    Activations Density 0.015%

    No Known Activations