© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81625
    Prev
    Next
    INDEX
    Explanations

    references to the classification of protein datasets and associated outcomes

    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
    ADS
    -0.06
    ALES
    -0.06
    UGHT
    -0.06
     pand
    -0.06
    ult
    -0.06
    åĨ
    -0.06
    owan
    -0.06
     Zug
    -0.06
     bi
    -0.06
     Ire
    -0.06
    POSITIVE LOGITS
     new
    0.10
    æĸ°çļĦ
    0.08
    Matchers
    0.08
    /new
    0.08
     новÑĭÑħ
    0.08
    new
    0.08
     test
    0.08
     новÑĭе
    0.08
    (new
    0.07
     nuevas
    0.07
    Activations Density 0.096%

    No Known Activations