© 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 EvalsExportsAPI 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. 125599
    Prev
    Next
    INDEX
    Explanations

    discussions related to statistical methods and analyses

    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
    emie
    -0.08
    ogany
    -0.08
    .openConnection
    -0.07
    段
    -0.07
    ÏĢη
    -0.07
    ãĤ¾
    -0.07
    kek
    -0.07
    ÏħÏĩ
    -0.07
    Ïĥμ
    -0.07
    duk
    -0.07
    POSITIVE LOGITS
     Eigen
    0.08
     eigen
    0.08
     eig
    0.08
     Eig
    0.07
     se
    0.07
     reconstruction
    0.07
     Orth
    0.07
    anker
    0.06
     basis
    0.06
     Spect
    0.06
    Activations Density 0.169%

    No Known Activations