© 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. 61762
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts related to macros and syntax structure

    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
    alten
    -0.07
    véd
    -0.07
    çĭ¬
    -0.07
    lesen
    -0.06
    anio
    -0.06
     Rein
    -0.06
     rempl
    -0.06
    eus
    -0.06
    oler
    -0.06
     pai
    -0.06
    POSITIVE LOGITS
     itself
    0.09
     Ñģамой
    0.07
     directly
    0.06
    YP
    0.06
    afb
    0.06
    core
    0.06
    æ°¸ä¹ħ
    0.06
     main
    0.06
    _LOGGER
    0.06
    ãģ¾ãĤĭ
    0.06
    Activations Density 0.031%

    No Known Activations