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. 22-LLAMASCOPE-RES-131K
    6. 5726
    Prev
    Next
    INDEX
    Explanations

    references to standards, guidelines, or conditions in various 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
     Schro
    -0.07
     Than
    -0.06
    ige
    -0.06
    kiye
    -0.06
    ibox
    -0.06
    infeld
    -0.06
    stra
    -0.06
     Chron
    -0.06
    _FORWARD
    -0.06
    wow
    -0.06
    POSITIVE LOGITS
    ritz
    0.07
    isson
    0.07
    adh
    0.06
    Cog
    0.06
    qui
    0.06
    á»Ŀi
    0.06
    à¹Ģสà¸Ļ
    0.06
    angu
    0.06
    utta
    0.06
    ussed
    0.06
    Activations Density 0.002%

    No Known Activations