© 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. 105020
    Prev
    Next
    INDEX
    Explanations

    references to educational or informational sources

    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
    .mvp
    -0.06
    .gdx
    -0.06
    æīĵ
    -0.06
    996
    -0.05
    697
    -0.05
     mart
    -0.05
     Kata
    -0.05
    çłģ
    -0.05
    åį
    -0.05
    agon
    -0.05
    POSITIVE LOGITS
    wik
    0.08
    .wp
    0.08
    contributors
    0.08
    æ¢Ŀ
    0.07
     داÙĨØ´ÙĨاÙħÙĩ
    0.07
    umlu
    0.07
    åĢī
    0.07
    Ø°
    0.07
     contributors
    0.07
    .wikipedia
    0.07
    Activations Density 0.004%

    No Known Activations