© 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. 129275
    Prev
    Next
    INDEX
    Explanations

    instances of the word "turn" in contexts related to performance or participation

    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
    ulton
    -0.07
    lesh
    -0.06
    åł¡
    -0.06
    quine
    -0.06
    Subview
    -0.06
    heel
    -0.06
     mName
    -0.06
    ILA
    -0.06
    олева
    -0.06
    UN
    -0.06
    POSITIVE LOGITS
    اÙĩ
    0.07
    reeNode
    0.07
    usu
    0.07
    ioneer
    0.07
    YLES
    0.07
    (es
    0.06
    ưa
    0.06
     to
    0.06
    asted
    0.06
    [last
    0.06
    Activations Density 0.003%

    No Known Activations