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. 43602
    Prev
    Next
    INDEX
    Explanations

    elements related to food and drink, especially in a culinary context

    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
     Qed
    -0.07
    ÏģοÏĤ
    -0.07
    /plugins
    -0.07
    kits
    -0.06
    ané
    -0.06
    ì²ł
    -0.06
     Microwave
    -0.06
     Kabul
    -0.06
    .Transactional
    -0.06
    altung
    -0.06
    POSITIVE LOGITS
     cogn
    0.21
     Hen
    0.15
     VS
    0.13
    Hen
    0.12
     liquor
    0.12
     XO
    0.12
     spirits
    0.12
     dist
    0.11
     cognition
    0.10
     lique
    0.10
    Activations Density 0.007%

    No Known Activations