© 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. 30707
    Prev
    Next
    INDEX
    Explanations

    references to specific statistics or numerical data

    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
     hát
    -0.07
    yle
    -0.06
    Å©i
    -0.06
    ÙĴت
    -0.06
     amaç
    -0.06
    217
    -0.06
    545
    -0.06
    ÑĥзÑĭ
    -0.06
     Supplies
    -0.05
     “âĢ¦
    -0.05
    POSITIVE LOGITS
     item
    0.09
     items
    0.09
    items
    0.08
    item
    0.08
     popular
    0.07
     ITEM
    0.07
     ones
    0.07
     games
    0.07
    _item
    0.06
     Item
    0.06
    Activations Density 0.041%

    No Known Activations