© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 1374
    Prev
    Next
    INDEX
    Explanations

    deadlines and dates for submissions or applications

    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
    maktan
    -0.06
    gen
    -0.06
    dan
    -0.06
    vers
    -0.06
    anc
    -0.06
    izable
    -0.06
    262
    -0.06
    ết
    -0.06
    /gpio
    -0.06
    569
    -0.06
    POSITIVE LOGITS
    .Restr
    0.08
    pha
    0.07
    orde
    0.07
    ï¸
    0.07
    aster
    0.07
    Ñĩно
    0.07
    praak
    0.06
    à¹īà¸ĩ
    0.06
    .zh
    0.06
     Huffman
    0.06
    Activations Density 0.004%

    No Known Activations