© 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. 105790
    Prev
    Next
    INDEX
    Explanations

    HTML and other markup language tags

    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
    обÑĢаз
    -0.06
    oplast
    -0.06
    plies
    -0.06
    á»ı
    -0.06
    RIC
    -0.06
    uber
    -0.06
    alist
    -0.06
    ÙĨا
    -0.06
    ervlet
    -0.06
    [
    -0.06
    POSITIVE LOGITS
    emez
    0.07
    545
    0.07
    DataExchange
    0.07
    DataContract
    0.07
     body
    0.06
    anka
    0.06
    body
    0.06
    olls
    0.06
    <html
    0.06
     FieldType
    0.06
    Activations Density 0.016%

    No Known Activations