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. 43821
    Prev
    Next
    INDEX
    Explanations

    recipes and ingredients related to pizza and meals

    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
    iÄį
    -0.07
     ubyt
    -0.07
    romatic
    -0.07
    елÑİ
    -0.07
    yled
    -0.07
    ré
    -0.06
    uggy
    -0.06
    becue
    -0.06
    askell
    -0.06
    unda
    -0.06
    POSITIVE LOGITS
     Trader
    0.10
     store
    0.10
     trader
    0.10
     regular
    0.09
     organic
    0.09
     already
    0.09
     left
    0.09
     Newman
    0.08
     Weg
    0.08
     TJ
    0.08
    Activations Density 0.051%

    No Known Activations