© 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. 85799
    Prev
    Next
    INDEX
    Explanations

    references to medical procedures and 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
    Äįit
    -0.08
    olley
    -0.07
    adaki
    -0.07
     clinically
    -0.07
    å·
    -0.07
    cce
    -0.07
    langs
    -0.07
    otte
    -0.07
    ury
    -0.06
     Ung
    -0.06
    POSITIVE LOGITS
     candidacy
    0.10
     suitability
    0.07
     candidates
    0.07
    agem
    0.07
     ideal
    0.07
     appropri
    0.07
     Candidates
    0.07
    SessionFactory
    0.06
     Ris
    0.06
    ideal
    0.06
    Activations Density 0.030%

    No Known Activations