Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 95579
    Prev
    Next
    INDEX
    Explanations

    terms related to health insurance and coverage

    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
    stad
    -0.07
     dow
    -0.07
    atory
    -0.07
    ari
    -0.06
     bail
    -0.06
    _CAST
    -0.06
    ä¸Ī
    -0.06
    .pkg
    -0.06
     dr
    -0.06
    irty
    -0.06
    POSITIVE LOGITS
    loh
    0.07
    uka
    0.06
     Gur
    0.06
    fcc
    0.06
    Compose
    0.06
    oke
    0.06
    ipc
    0.06
    amaged
    0.05
    ÃŃc
    0.05
    aben
    0.05
    Activations Density 0.003%

    No Known Activations