© 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. 76796
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical treatments and their effects on patients with multiple sclerosis

    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
    /misc
    -0.06
     Relief
    -0.06
    iets
    -0.06
     Surge
    -0.06
     Rodgers
    -0.06
    ilm
    -0.05
    805
    -0.05
    à¸Ľà¸£à¸°à¸ª
    -0.05
    (Cell
    -0.05
     Gir
    -0.05
    POSITIVE LOGITS
    inton
    0.08
     consenting
    0.07
    elor
    0.07
    hsi
    0.07
    iev
    0.07
    alled
    0.07
    odia
    0.07
    æĻļ
    0.07
    Ưá»
    0.07
    ç¿Ĵ
    0.07
    Activations Density 0.017%

    No Known Activations