© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 30034
    Prev
    Next
    INDEX
    Explanations

    programming or scripting commands related to visibility and conditional logic

    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
    лав
    -0.06
    aeda
    -0.06
     stock
    -0.06
    -stock
    -0.05
    stock
    -0.05
     wards
    -0.05
    idar
    -0.05
    itzerland
    -0.05
    ÑĨÑĮ
    -0.05
     ÎĴα
    -0.05
    POSITIVE LOGITS
    ocos
    0.08
    .bc
    0.07
    inalg
    0.07
     Kauf
    0.07
    rof
    0.07
    .openg
    0.06
    DownList
    0.06
    PWM
    0.06
    /tiny
    0.06
    ëĬIJ
    0.06
    Activations Density 0.000%

    No Known Activations