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. 44154
    Prev
    Next
    INDEX
    Explanations

    references to safety protocols and guidelines related to health precautions

    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
     Dân
    -0.06
     Discord
    -0.06
    Û²Û°Û²
    -0.06
    çŃĭ
    -0.06
     Roe
    -0.06
     PyQt
    -0.05
     Rowe
    -0.05
     scarc
    -0.05
     lockdown
    -0.05
    .getNode
    -0.05
    POSITIVE LOGITS
     cleanliness
    0.12
     cleaning
    0.11
     guest
    0.11
     Guest
    0.11
     Cleaning
    0.11
     hygiene
    0.11
     sanitation
    0.11
     Clean
    0.10
     guests
    0.10
     sanit
    0.10
    Activations Density 0.006%

    No Known Activations