© 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 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. 71272
    Prev
    Next
    INDEX
    Explanations

    URLs and their formats

    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
     gó
    -0.07
    roud
    -0.07
    iyah
    -0.07
    quia
    -0.06
    emat
    -0.06
    oulos
    -0.06
    зÑĮ
    -0.06
    ãn
    -0.06
    опол
    -0.06
     counts
    -0.06
    POSITIVE LOGITS
    anel
    0.07
    大åħ¨
    0.07
     Hart
    0.06
     sust
    0.06
    izen
    0.06
    عاÙĦ
    0.05
     abb
    0.05
    ANEL
    0.05
     Booker
    0.05
     abstract
    0.05
    Activations Density 0.001%

    No Known Activations