© 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. 86692
    Prev
    Next
    INDEX
    Explanations

    references to research studies and their findings

    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
     Ä°nsan
    -0.08
     baģlantılar
    -0.07
    tra
    -0.07
     DÃ¼ÅŁ
    -0.07
    æĹıèĩªæ²»
    -0.07
     Hiç
    -0.07
    ÅĤy
    -0.07
    APE
    -0.06
     Düny
    -0.06
     Ãľst
    -0.06
    POSITIVE LOGITS
     ı
    0.09
    èĦ±
    0.07
    ovali
    0.07
     Paz
    0.07
     Sey
    0.07
    .Sin
    0.07
    opak
    0.07
    &uuml
    0.07
    etten
    0.07
     Madd
    0.07
    Activations Density 0.129%

    No Known Activations