© 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. 16867
    Prev
    Next
    INDEX
    Explanations

    any sections of textual content containing numerical values or addresses

    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
    аÑĢд
    -0.08
    orer
    -0.07
    anki
    -0.07
    cz
    -0.06
    hangi
    -0.06
    oya
    -0.06
    indr
    -0.06
    ynos
    -0.06
    ifar
    -0.06
    unar
    -0.06
    POSITIVE LOGITS
    ogan
    0.06
    ¶Ī
    0.06
    eden
    0.06
     Shopping
    0.06
     anv
    0.06
     Bot
    0.06
    ean
    0.06
    kbd
    0.06
    ouncy
    0.06
    plode
    0.06
    Activations Density 0.000%

    No Known Activations