© 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. 9-LLAMASCOPE-RES-131K
    11. 95303
    Prev
    Next
    INDEX
    Explanations

    percentage or dollar sign indicators in data

    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
    isay
    -0.07
    nis
    -0.07
    otty
    -0.07
    acho
    -0.06
    erialize
    -0.06
    vise
    -0.06
    inic
    -0.06
    eous
    -0.06
    imei
    -0.06
    .opts
    -0.06
    POSITIVE LOGITS
    æİ
    0.06
    urette
    0.06
     Dart
    0.06
     StatusBar
    0.06
     dab
    0.06
    èĥİ
    0.06
     Separate
    0.06
     conscience
    0.06
    groundColor
    0.06
     blitz
    0.06
    Activations Density 0.000%

    No Known Activations