© 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. 485
    Prev
    Next
    INDEX
    Explanations

    references to "smart" products or technologies

    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
    htar
    -0.08
    bjerg
    -0.08
    naires
    -0.08
    ps
    -0.08
    aires
    -0.07
    ureka
    -0.07
    naire
    -0.07
    aire
    -0.07
    ese
    -0.07
    esh
    -0.07
    POSITIVE LOGITS
    ness
    0.09
    ies
    0.08
    son
    0.08
    ened
    0.08
    ypad
    0.08
    inez
    0.07
    ly
    0.07
    608
    0.07
    à¸Ľà¸£à¸°à¸Īำ
    0.07
    cape
    0.07
    Activations Density 0.008%

    No Known Activations