© 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 EvalsExportsAPI 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. 82961
    Prev
    Next
    INDEX
    Explanations

    syntax and structural components in programming code

    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
    inct
    -0.09
    oded
    -0.07
    ylko
    -0.07
    eldorf
    -0.07
    empl
    -0.06
    ystate
    -0.06
    amba
    -0.06
    ump
    -0.06
    acha
    -0.06
    preneur
    -0.06
    POSITIVE LOGITS
    alias
    0.07
     alias
    0.07
    breadcrumb
    0.07
    allen
    0.07
     pushViewController
    0.06
     dikke
    0.06
     kli
    0.06
    ãĥ©ãĤ¤ãĥĪ
    0.06
     dün
    0.06
     Kür
    0.06
    Activations Density 0.049%

    No Known Activations