© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1290
    Prev
    Next
    INDEX
    Explanations

    HTML language attributes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    iland
    -0.08
    iazza
    -0.07
     Lifetime
    -0.07
     Goldberg
    -0.07
     onBlur
    -0.07
     còn
    -0.06
    vise
    -0.06
    vrier
    -0.06
    åĬª
    -0.06
    537
    -0.06
    POSITIVE LOGITS
    ancel
    0.06
    ãĥªãĥ³
    0.06
    .scalablytyped
    0.06
    олаг
    0.06
    iment
    0.06
     ìĤ¬
    0.06
    _CONSOLE
    0.05
    RCT
    0.05
    práv
    0.05
    ialect
    0.05
    Activations Density 0.000%

    No Known Activations