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. 43997
    Prev
    Next
    INDEX
    Explanations

    actions related to food preparation and cooking techniques

    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
    Its
    -0.07
    åıĬåħ¶
    -0.07
     Its
    -0.06
    /my
    -0.06
    ogui
    -0.06
    ÑİÑĢ
    -0.06
    its
    -0.06
     коÑĤоÑĢого
    -0.06
    esome
    -0.06
     jego
    -0.06
    POSITIVE LOGITS
     them
    0.14
     contents
    0.12
     everything
    0.12
     your
    0.12
     each
    0.11
     mixture
    0.11
     the
    0.10
     entire
    0.10
    them
    0.10
    ixture
    0.09
    Activations Density 0.074%

    No Known Activations