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. 43640
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters

    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
     standardized
    -0.08
     centralized
    -0.07
     utilizes
    -0.07
     organizers
    -0.07
     legalize
    -0.07
    organization
    -0.07
     utilize
    -0.07
     Organizations
    -0.06
    organized
    -0.06
     organize
    -0.06
    POSITIVE LOGITS
     DF
    0.10
     China
    0.10
     Turnbull
    0.10
     Indonesia
    0.10
     Canberra
    0.09
     Australia
    0.09
     US
    0.09
     ASE
    0.09
     defence
    0.09
     Japan
    0.09
    Activations Density 0.006%

    No Known Activations