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. 44251
    Prev
    Next
    INDEX
    Explanations

    references to environmental regulations and water quality control measures

    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
    avad
    -0.07
    emark
    -0.07
    oice
    -0.07
    obot
    -0.07
    BOT
    -0.07
    ово
    -0.07
     LENG
    -0.07
    mars
    -0.06
     Rental
    -0.06
    .seed
    -0.06
    POSITIVE LOGITS
     nutrient
    0.15
     phosph
    0.14
     nitrogen
    0.13
     Nut
    0.13
     nutrients
    0.12
     pollut
    0.11
     Nit
    0.11
     nit
    0.10
    Nut
    0.10
     loading
    0.10
    Activations Density 0.033%

    No Known Activations