© 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. 28326
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or origins of issues

    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
    uga
    -0.07
    ãĥ¼ãĥľ
    -0.07
    .kotlin
    -0.07
    mant
    -0.07
    коÑĤ
    -0.07
    ÑĨик
    -0.07
    tero
    -0.06
    ë²Ķ
    -0.06
    kili
    -0.06
    ,{"
    -0.06
    POSITIVE LOGITS
     lack
    0.09
    /to
    0.06
     use
    0.06
    use
    0.06
     such
    0.06
    herent
    0.06
     usage
    0.06
    such
    0.06
     Lack
    0.06
     falta
    0.06
    Activations Density 0.039%

    No Known Activations