© 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. 93446
    Prev
    Next
    INDEX
    Explanations

    mentions of diseases

    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
     Tos
    -0.07
    vap
    -0.07
    ould
    -0.07
    dra
    -0.06
    lei
    -0.06
    ÄĽr
    -0.06
    èo
    -0.06
    Į
    -0.06
    upal
    -0.06
    andro
    -0.06
    POSITIVE LOGITS
     sometimes
    0.06
    erten
    0.06
     importantly
    0.06
     important
    0.06
     like
    0.06
     pa
    0.06
    yy
    0.06
    ÏģÏĮ
    0.06
    äºĭ
    0.06
    ickets
    0.06
    Activations Density 0.000%

    No Known Activations