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

    Neuronpedia

    Jacobian LensNEW
    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. 59286
    Prev
    Next
    INDEX
    Explanations

    medical conditions and their related causes

    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
    otime
    -0.07
    berger
    -0.07
    ardon
    -0.07
    δε
    -0.07
    ÐľÐŀ
    -0.07
    .Deserialize
    -0.07
    OMPI
    -0.07
    archy
    -0.07
    uhe
    -0.07
    èħ
    -0.07
    POSITIVE LOGITS
     disease
    0.07
     tra
    0.07
     trauma
    0.07
     damage
    0.06
     dam
    0.06
     chemicals
    0.06
    ÏĦÏģα
    0.06
     Dam
    0.06
     Overse
    0.06
    emmel
    0.06
    Activations Density 0.026%

    No Known Activations