© 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. 72334
    Prev
    Next
    INDEX
    Explanations

    symbols and operators used in programming or code syntax

    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
    ردÙĩ
    -0.08
    heed
    -0.07
     Madden
    -0.07
     Kle
    -0.07
    çĴ°
    -0.06
    aken
    -0.06
     èIJ
    -0.06
     kle
    -0.06
    ½
    -0.06
    akra
    -0.06
    POSITIVE LOGITS
    icit
    0.07
    abus
    0.07
    nev
    0.06
    )((((
    0.06
     zeroes
    0.06
     nullptr
    0.06
    _UNS
    0.06
    iday
    0.06
    (IDC
    0.06
    sys
    0.06
    Activations Density 0.152%

    No Known Activations