© 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. 77607
    Prev
    Next
    INDEX
    Explanations

    country names and their shipping relevance

    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
    ade
    -0.07
    ADE
    -0.06
    ijing
    -0.06
    ehler
    -0.06
    gent
    -0.06
    tle
    -0.06
    ogh
    -0.06
    phalt
    -0.06
    gang
    -0.06
    LOB
    -0.06
    POSITIVE LOGITS
    âĦĸ
    0.07
    çŃĴ
    0.07
    _ut
    0.07
    annis
    0.06
    .ut
    0.06
     Canter
    0.06
     UObject
    0.06
    ابة
    0.06
    港
    0.06
     safeg
    0.06
    Activations Density 0.002%

    No Known Activations