© 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. 74852
    Prev
    Next
    INDEX
    Explanations

    details related to medical professionals and their affiliations

    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
     whilst
    -0.08
     Whilst
    -0.07
     excer
    -0.07
    Cad
    -0.07
    \:
    -0.07
    .CreateInstance
    -0.07
    Whilst
    -0.06
    odega
    -0.06
    ARDS
    -0.06
     amongst
    -0.06
    POSITIVE LOGITS
     Downtown
    0.07
     Gov
    0.07
     globe
    0.07
     last
    0.07
    itel
    0.06
     downtown
    0.06
     pending
    0.06
    ãĥ³ãĤ°
    0.06
    riz
    0.06
     county
    0.06
    Activations Density 0.089%

    No Known Activations