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. 43491
    Prev
    Next
    INDEX
    Explanations

    references to state-owned enterprises and related economic structures

    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
     Raq
    -0.07
    pga
    -0.06
    Manifest
    -0.06
    PGA
    -0.06
    antis
    -0.06
     Yas
    -0.06
     Duffy
    -0.06
     Fla
    -0.06
     DropIndex
    -0.06
    imals
    -0.06
    POSITIVE LOGITS
     PSU
    0.12
     PS
    0.09
     Public
    0.09
     Engineers
    0.09
     ps
    0.09
     Oil
    0.09
     public
    0.08
     sick
    0.08
    ÂłPS
    0.08
     Shipping
    0.08
    Activations Density 0.009%

    No Known Activations