© 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. 87236
    Prev
    Next
    INDEX
    Explanations

    references to medical data and clinical contexts

    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
    teÅŁ
    -0.07
    ansson
    -0.06
    _attach
    -0.06
    à¸į
    -0.06
     ÑĢÑĥÑĩ
    -0.06
    веÑī
    -0.06
    oui
    -0.06
     pás
    -0.06
    ü
    -0.06
    ÑĢеÑĪ
    -0.06
    POSITIVE LOGITS
    -REAL
    0.07
     hip
    0.07
    ysa
    0.06
    Coverage
    0.06
    icker
    0.06
    515
    0.06
     records
    0.06
    _ALIGN
    0.06
     summons
    0.06
    Records
    0.06
    Activations Density 0.042%

    No Known Activations