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. 5531
    Prev
    Next
    INDEX
    Explanations

    terms related to breastfeeding and its impact on health

    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
    emma
    -0.07
    ishi
    -0.07
    gd
    -0.07
    许
    -0.07
    ags
    -0.07
    gx
    -0.07
    ITIES
    -0.07
    ä¼į
    -0.07
    nun
    -0.06
     ObjectId
    -0.06
    POSITIVE LOGITS
     Mother
    0.07
    able
    0.07
     duration
    0.07
    -friendly
    0.07
     Friendly
    0.07
    uits
    0.06
     mother
    0.06
    Mother
    0.06
     friendly
    0.06
     consultant
    0.06
    Activations Density 0.002%

    No Known Activations