© 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. 83026
    Prev
    Next
    INDEX
    Explanations

    terminology and expressions related to medical conditions and their characteristics

    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
    olie
    -0.07
     suspects
    -0.06
    åłĤ
    -0.06
    zeug
    -0.06
    vie
    -0.06
     Tong
    -0.06
     Yoshi
    -0.06
    ervers
    -0.06
    .echo
    -0.05
    okol
    -0.05
    POSITIVE LOGITS
    NCY
    0.08
    RITE
    0.08
     Indicator
    0.07
    .scalablytyped
    0.07
    ynes
    0.07
    rtc
    0.07
    agens
    0.07
    кÑĢаÑĹ
    0.07
    ktop
    0.07
     indicator
    0.07
    Activations Density 0.024%

    No Known Activations