© 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. 28883
    Prev
    Next
    INDEX
    Explanations

    terms related to medical devices and their functionalities

    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
    CCR
    -0.07
    .visualization
    -0.06
    ambre
    -0.06
    inion
    -0.06
     éĸ¢éĢ£
    -0.06
    ksiyon
    -0.06
    821
    -0.06
    autiful
    -0.06
    cks
    -0.06
    ctp
    -0.06
    POSITIVE LOGITS
     civilian
    0.06
    ARTH
    0.06
    æĬķ
    0.06
    quares
    0.06
     Ratings
    0.06
    ogh
    0.06
    à¥įरण
    0.06
     iff
    0.05
    -generation
    0.05
     xen
    0.05
    Activations Density 0.001%

    No Known Activations