© 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. 108538
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    umber
    -0.06
     dit
    -0.06
     COPYING
    -0.06
    oyer
    -0.06
    Untitled
    -0.06
    代
    -0.06
    aut
    -0.06
     HIS
    -0.05
    velop
    -0.05
     Auxiliary
    -0.05
    POSITIVE LOGITS
    à¥
    0.08
    anje
    0.08
    alaxy
    0.07
    ternet
    0.07
    è¨Ģãģ£ãģŁ
    0.07
    AYS
    0.07
    class
    0.07
    	class
    0.07
    593
    0.07
    #:
    0.07
    Activations Density 0.009%

    No Known Activations