© 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. 59435
    Prev
    Next
    INDEX
    Explanations

    code functions and conditional expressions

    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
    ëĭĿ
    -0.07
     Natur
    -0.07
    λÏī
    -0.07
     zem
    -0.06
    bu
    -0.06
    oger
    -0.06
    ìħĺ
    -0.06
    Sugar
    -0.06
     Unidos
    -0.06
    io
    -0.06
    POSITIVE LOGITS
     Kir
    0.07
    ìĥ
    0.07
    Kir
    0.06
     count
    0.06
    ENU
    0.06
     stret
    0.06
    ccount
    0.06
    .abstract
    0.06
     Stretch
    0.06
    hil
    0.06
    Activations Density 0.021%

    No Known Activations