© 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. 116923
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and annotations

    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
    ook
    -0.07
    iná
    -0.06
    Languages
    -0.06
    mey
    -0.06
    issen
    -0.06
    urgeon
    -0.06
    bern
    -0.06
     Seymour
    -0.06
    370
    -0.06
    eton
    -0.06
    POSITIVE LOGITS
     Obl
    0.07
    ewise
    0.06
    fec
    0.06
    emiz
    0.06
     Fel
    0.06
    aft
    0.06
    .Require
    0.06
    oks
    0.06
    çºĮ
    0.06
     adaptation
    0.06
    Activations Density 0.000%

    No Known Activations