© 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. 79862
    Prev
    Next
    INDEX
    Explanations

    references to digital object identifiers (DOIs) in academic articles

    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
    ëĭ¤ê°Ģ
    -0.07
    pite
    -0.06
    αÏĢÏĮ
    -0.06
    ople
    -0.06
    xCC
    -0.06
     Hammond
    -0.06
    igli
    -0.06
    insky
    -0.06
     sik
    -0.06
    emer
    -0.06
    POSITIVE LOGITS
    .gov
    0.07
    247
    0.07
    .org
    0.06
    berman
    0.06
    .googleapis
    0.06
    ourcem
    0.06
    hold
    0.06
    же
    0.06
    hower
    0.06
    ÙĨب
    0.06
    Activations Density 0.002%

    No Known Activations