© 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. 17-LLAMASCOPE-RES-131K
    11. 108488
    Prev
    Next
    INDEX
    Explanations

    keywords related to academic and professional qualifications in the field of dentistry and healthcare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Professional position titles and job roles appearing in resume or professional profile listings, often preceded by seniority level (e.g., "Senior") or followed by specialization areas.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    rawn
    -0.07
    \uc
    -0.07
    itler
    -0.06
    agements
    -0.06
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.06
    IMA
    -0.06
    edException
    -0.06
    èĢħ
    -0.06
    ären
    -0.06
     èĢħ
    -0.06
    POSITIVE LOGITS
     assistant
    0.14
     Assistant
    0.14
    Assistant
    0.12
    assistant
    0.11
     Associate
    0.10
     junior
    0.10
     assistants
    0.09
     associate
    0.09
     Junior
    0.08
    åī¯
    0.08
    Activations Density 0.254%

    No Known Activations