© 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. 15-LLAMASCOPE-RES-131K
    6. 103388
    Prev
    Next
    INDEX
    Explanations

    terms related to the immune system and inflammation responses

    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
    TOCOL
    -0.07
    åĩºåı£
    -0.07
     Fet
    -0.07
    clid
    -0.07
    UME
    -0.07
     å®®
    -0.06
    morgan
    -0.06
    ег
    -0.06
    ırak
    -0.06
    fen
    -0.06
    POSITIVE LOGITS
     immune
    0.07
    MLElement
    0.06
     Imm
    0.06
     forming
    0.06
     coal
    0.06
     immobil
    0.06
     freel
    0.06
    sembly
    0.06
     hon
    0.06
     Cascade
    0.06
    Activations Density 0.006%

    No Known Activations