© 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. 81901
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and structures

    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
    plash
    -0.06
    درÛĮ
    -0.05
     spin
    -0.05
     spinning
    -0.05
    PRESENT
    -0.05
    ãĥĥãĤ·ãĥ¥
    -0.05
    prise
    -0.05
     perform
    -0.05
     Amph
    -0.05
     species
    -0.05
    POSITIVE LOGITS
     plots
    0.08
     areas
    0.08
     territories
    0.07
    ajor
    0.07
     plot
    0.07
    istr
    0.07
    à¹Ħหà¸Ļ
    0.07
     Areas
    0.07
    asan
    0.07
    territ
    0.07
    Activations Density 0.010%

    No Known Activations