© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82495
    Prev
    Next
    INDEX
    Explanations

    references to multiple sclerosis and its associated medical treatments

    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
    cken
    -0.07
    iens
    -0.07
    /prom
    -0.07
    ppe
    -0.07
     viability
    -0.06
    /layouts
    -0.06
     layouts
    -0.06
    enger
    -0.06
     COPYING
    -0.06
    ovable
    -0.06
    POSITIVE LOGITS
     risk
    0.07
    ardin
    0.07
     secondary
    0.06
     com
    0.06
    esz
    0.06
     overlap
    0.06
     Mann
    0.06
    accel
    0.06
    èĦĤ
    0.06
     Weber
    0.06
    Activations Density 0.032%

    No Known Activations