© 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. 61005
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to specific diseases and their treatment

    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
    óa
    -0.08
    renom
    -0.08
    wers
    -0.08
     Campos
    -0.07
    bish
    -0.07
    rete
    -0.07
    _fx
    -0.07
    /******/
    -0.07
    villa
    -0.07
    lyph
    -0.07
    POSITIVE LOGITS
    ajo
    0.06
     vertical
    0.06
     Randall
    0.06
     Outlook
    0.06
     Budd
    0.05
     NAT
    0.05
    ttl
    0.05
    di
    0.05
    ,
    0.05
     horizontally
    0.05
    Activations Density 0.008%

    No Known Activations