© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78076
    Prev
    Next
    INDEX
    Explanations

    references to medical research, particularly involving gene therapy and stem cells

    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
    jez
    -0.06
    izo
    -0.06
    apid
    -0.06
    æĹ¦
    -0.06
     æ©
    -0.06
     items
    -0.05
     spoilers
    -0.05
    _chain
    -0.05
     spoil
    -0.05
    ÏĦαν
    -0.05
    POSITIVE LOGITS
     delivery
    0.11
     Delivery
    0.11
    Delivery
    0.10
     deliver
    0.10
    delivery
    0.10
     Deliver
    0.09
    deliver
    0.09
     delivered
    0.09
     delivering
    0.09
     carriers
    0.09
    Activations Density 0.022%

    No Known Activations