© 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. 124588
    Prev
    Next
    INDEX
    Explanations

    phrases indicating educational background and qualifications

    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
    ault
    -0.07
    iš
    -0.07
    rail
    -0.07
    istingu
    -0.07
    inges
    -0.06
    imate
    -0.06
    èĪį
    -0.06
    éĮ
    -0.06
    levard
    -0.06
     á»ķ
    -0.06
    POSITIVE LOGITS
     Exit
    0.06
    акон
    0.06
     Paths
    0.06
    bled
    0.06
     Eck
    0.05
    à¸ģรม
    0.05
     schools
    0.05
     commission
    0.05
    okt
    0.05
     ÑĪкол
    0.05
    Activations Density 0.007%

    No Known Activations