© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74544
    Prev
    Next
    INDEX
    Explanations

    terms related to diseases and scientific classifications

    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
     resend
    -0.08
     Nguyên
    -0.07
    unga
    -0.07
    iá»ĩn
    -0.07
    NSObject
    -0.07
    ailles
    -0.07
     cancell
    -0.07
    mana
    -0.07
    ego
    -0.07
    scss
    -0.07
    POSITIVE LOGITS
    aul
    0.07
     bust
    0.06
    ides
    0.06
    omorphic
    0.06
    onta
    0.06
    esthesia
    0.06
     poly
    0.05
    ,
    0.05
    andra
    0.05
     [
    0.05
    Activations Density 0.115%

    No Known Activations