© 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. 82769
    Prev
    Next
    INDEX
    Explanations

    topics related to healthcare facilities and their conditions

    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
    代çIJĨ
    -0.06
    aln
    -0.06
    jing
    -0.06
    \Migrations
    -0.06
    EMA
    -0.06
    altar
    -0.06
    rex
    -0.06
    Office
    -0.05
    ngr
    -0.05
    lei
    -0.05
    POSITIVE LOGITS
     facility
    0.09
    uckles
    0.07
     Facility
    0.07
     facilities
    0.07
    оба
    0.07
     abroad
    0.07
    inery
    0.07
    presso
    0.07
     bills
    0.07
    adero
    0.07
    Activations Density 0.031%

    No Known Activations