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. 44008
    Prev
    Next
    INDEX
    Explanations

    references to pork and related dishes

    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
    DialogTitle
    -0.07
    unker
    -0.07
    ória
    -0.07
    atego
    -0.07
    aylight
    -0.07
    اÙħÙĩ
    -0.06
    .datatables
    -0.06
    ë¯
    -0.06
    nty
    -0.06
    ials
    -0.06
    POSITIVE LOGITS
    chop
    0.15
     belly
    0.14
     shoulder
    0.13
     loin
    0.13
     chops
    0.13
    etta
    0.13
     chop
    0.12
     Shoulder
    0.12
    bel
    0.12
     ribs
    0.11
    Activations Density 0.008%

    No Known Activations