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. 5698
    Prev
    Next
    INDEX
    Explanations

    culinary techniques involving sautéing or cooking methods

    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
    rame
    -0.08
    dess
    -0.07
    ru
    -0.07
    luž
    -0.07
     Dess
    -0.07
    sher
    -0.07
    night
    -0.07
     ActionTypes
    -0.07
     Lords
    -0.07
    etch
    -0.07
    POSITIVE LOGITS
    Ìģ
    0.07
    eing
    0.07
    roupe
    0.07
    -style
    0.07
     style
    0.06
     Sa
    0.06
    /rc
    0.06
    inge
    0.06
     Sez
    0.06
     sa
    0.06
    Activations Density 0.006%

    No Known Activations