© 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. 118787
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structure in 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
    iska
    -0.09
    sterol
    -0.08
    abyrinth
    -0.08
    raci
    -0.08
    EIF
    -0.08
    .TestTools
    -0.07
    éli
    -0.07
    iggins
    -0.07
    jte
    -0.07
    emple
    -0.07
    POSITIVE LOGITS
     Canter
    0.06
     transition
    0.06
     æĪ
    0.06
    iana
    0.06
    ocker
    0.06
    aps
    0.05
    ,
    0.05
     g
    0.05
     per
    0.05
     alloc
    0.05
    Activations Density 0.008%

    No Known Activations