© 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. 106887
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical terminology related to medical tests

    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
    ç´Ļ
    -0.08
    raya
    -0.07
    eÅŁ
    -0.07
    acam
    -0.07
     UIEdgeInsets
    -0.07
    aryl
    -0.06
    ighton
    -0.06
    dent
    -0.06
     polls
    -0.06
    appointment
    -0.06
    POSITIVE LOGITS
     ëĤ
    0.07
     y
    0.06
     hus
    0.06
     Marketing
    0.06
    /inet
    0.06
     marketing
    0.06
    PropertyDescriptor
    0.06
     X
    0.06
    icut
    0.06
    age
    0.06
    Activations Density 0.009%

    No Known Activations