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. 44041
    Prev
    Next
    INDEX
    Explanations

    data points related to measurements or identifiers within medical or structured contexts

    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
    anders
    -0.07
    omik
    -0.07
    μβ
    -0.06
    BOSE
    -0.06
     armour
    -0.06
    нина
    -0.06
     FAT
    -0.06
    endor
    -0.06
     neighbours
    -0.06
    iswa
    -0.06
    POSITIVE LOGITS
     rankings
    0.11
     Honor
    0.11
     Rankings
    0.10
     specialties
    0.10
     specialty
    0.09
     metro
    0.09
     Best
    0.09
     ranking
    0.09
     pul
    0.09
     nationally
    0.09
    Activations Density 0.003%

    No Known Activations