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. 44224
    Prev
    Next
    INDEX
    Explanations

    economic issues and challenges

    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
    รà¸Ńà¸ļ
    -0.07
     Seeder
    -0.07
    uzey
    -0.07
    ntl
    -0.07
    otec
    -0.07
    /includes
    -0.06
    -regexp
    -0.06
    κÏħ
    -0.06
    elez
    -0.06
     annoying
    -0.06
    POSITIVE LOGITS
     strain
    0.11
     strains
    0.11
     stresses
    0.10
     strife
    0.10
     stress
    0.10
     tur
    0.10
     mel
    0.09
     distress
    0.09
     uncertainty
    0.09
     tumult
    0.09
    Activations Density 0.031%

    No Known Activations