© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87877
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical consultations and treatment options

    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
    adian
    -0.07
     ydk
    -0.07
    Å¡ov
    -0.07
     vÄĽ
    -0.07
    genesis
    -0.06
    oidal
    -0.06
    uner
    -0.06
     Leopard
    -0.06
    avad
    -0.06
    aurus
    -0.06
    POSITIVE LOGITS
    376
    0.06
     determine
    0.06
     isot
    0.06
     Hart
    0.06
    esser
    0.05
    atism
    0.05
    076
    0.05
     determin
    0.05
     referral
    0.05
     Mile
    0.05
    Activations Density 0.008%

    No Known Activations