© 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. 15-LLAMASCOPE-RES-131K
    6. 90597
    Prev
    Next
    INDEX
    Explanations

    numeric values and formatting related to categories and classifications

    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
    ajÄħc
    -0.06
    vr
    -0.06
    766
    -0.06
    elden
    -0.06
    943
    -0.06
     Kapoor
    -0.06
     pocket
    -0.06
     Mev
    -0.06
    erp
    -0.06
    raud
    -0.06
    POSITIVE LOGITS
    rets
    0.08
    uers
    0.06
    utex
    0.06
    awa
    0.06
    âĨĴâĨĴ
    0.06
    _BLK
    0.06
    /Instruction
    0.06
    sehen
    0.06
    /Library
    0.06
    inode
    0.06
    Activations Density 0.040%

    No Known Activations