© 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. 56913
    Prev
    Next
    INDEX
    Explanations

    comparisons between car models and their features

    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
    hausen
    -0.07
    erdale
    -0.07
    .scalablytyped
    -0.07
    аÑĢам
    -0.07
    гл
    -0.06
    essen
    -0.06
    .MixedReality
    -0.06
    umas
    -0.06
    .ham
    -0.06
    -specific
    -0.06
    POSITIVE LOGITS
    edin
    0.06
    wid
    0.06
     offerings
    0.06
    tek
    0.06
     æ´
    0.06
    ipers
    0.06
     Noon
    0.06
    pek
    0.06
    RIPT
    0.06
    åĢ
    0.05
    Activations Density 0.017%

    No Known Activations