© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77531
    Prev
    Next
    INDEX
    Explanations

    phrases related to public health and safety 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
     Maison
    -0.06
    ayne
    -0.06
     heck
    -0.06
    hell
    -0.06
    avs
    -0.06
    burgh
    -0.06
    lement
    -0.06
    berman
    -0.06
    éné
    -0.06
    ame
    -0.06
    POSITIVE LOGITS
     loved
    0.07
     health
    0.07
     Health
    0.07
     community
    0.07
     nues
    0.07
    émon
    0.07
     Beds
    0.06
     transmissions
    0.06
    community
    0.06
     Loved
    0.06
    Activations Density 0.011%

    No Known Activations