© 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. 5-LLAMASCOPE-RES-131K
    11. 126763
    Prev
    Next
    INDEX
    Explanations

    phrases signaling contradictions or surprises in context

    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
    lei
    -0.06
    ála
    -0.06
    idar
    -0.06
    490
    -0.06
    apur
    -0.06
    اد
    -0.06
    ua
    -0.06
    ÙĬد
    -0.06
    erg
    -0.06
     Meal
    -0.06
    POSITIVE LOGITS
    ıklı
    0.07
    ertype
    0.07
    aunch
    0.06
    Rendering
    0.06
     damp
    0.06
     dipl
    0.06
     Mint
    0.06
    ëłĩ
    0.06
    ån
    0.06
    dre
    0.06
    Activations Density 0.120%

    No Known Activations