© 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. 2073
    Prev
    Next
    INDEX
    Explanations

    recent evidence or data related to advancements, findings, or trends across various fields

    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
    æĸ¹éĿ¢
    -0.07
     tomorrow
    -0.07
     today
    -0.07
    æľĢåĪĿ
    -0.07
    currently
    -0.06
    å½ĵåīį
    -0.06
    pio
    -0.06
    enge
    -0.06
     currently
    -0.06
    iolet
    -0.06
    POSITIVE LOGITS
    eler
    0.09
    /current
    0.08
     additions
    0.07
     trends
    0.07
     addition
    0.07
     Trends
    0.07
    igon
    0.07
    fony
    0.06
    avenport
    0.06
    've
    0.06
    Activations Density 0.033%

    No Known Activations