© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 79094
    Prev
    Next
    INDEX
    Explanations

    numerical representations or values related to measurement or calculation

    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
    WARE
    -0.08
    ëĭĿ
    -0.07
    à¥įà¤ł
    -0.07
    ARTH
    -0.07
    vou
    -0.07
    azzo
    -0.07
    .getInteger
    -0.07
    ekil
    -0.07
    luv
    -0.07
    <>
    -0.07
    POSITIVE LOGITS
    ipa
    0.06
    keypress
    0.06
    asha
    0.06
    porto
    0.06
     -
    0.06
    ika
    0.06
    bsp
    0.05
     (
    0.05
    ongoose
    0.05
    çļĦæĥħ
    0.05
    Activations Density 0.001%

    No Known Activations