© 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. 15-LLAMASCOPE-RES-131K
    11. 104348
    Prev
    Next
    INDEX
    Explanations

    references to graphical or visual elements in documents

    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
    awan
    -0.08
    ought
    -0.07
    jni
    -0.07
    .restore
    -0.06
    incy
    -0.06
    ê·Ģ
    -0.06
    orie
    -0.06
    оÑĢе
    -0.06
    ynch
    -0.06
     Thief
    -0.06
    POSITIVE LOGITS
     glo
    0.07
    oon
    0.07
    ayout
    0.06
     crem
    0.06
    ITU
    0.06
     fus
    0.06
    _tooltip
    0.06
     selber
    0.06
    ums
    0.06
    廳
    0.06
    Activations Density 0.000%

    No Known Activations