© 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. 432
    Prev
    Next
    INDEX
    Explanations

    terms related to competition or ranking

    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
    heel
    -0.07
    aken
    -0.07
    brook
    -0.07
     nomine
    -0.07
    aldo
    -0.06
    iger
    -0.06
    cbc
    -0.06
    League
    -0.06
    /logging
    -0.06
    ully
    -0.06
    POSITIVE LOGITS
    arel
    0.07
    sworth
    0.07
    ãĢģãĢĬ
    0.06
    تÙĬÙĨ
    0.06
    471
    0.06
     Yates
    0.06
    osphere
    0.06
    ray
    0.06
    OLON
    0.06
    olon
    0.06
    Activations Density 0.017%

    No Known Activations