© 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. 17-LLAMASCOPE-RES-131K
    11. 93427
    Prev
    Next
    INDEX
    Explanations

    references to the word "flip" in various contexts

    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
    assen
    -0.08
    llib
    -0.07
    inea
    -0.07
    име
    -0.07
    hoo
    -0.07
    culate
    -0.07
    TickCount
    -0.07
    åĿĬ
    -0.07
    ivel
    -0.06
    estro
    -0.06
    POSITIVE LOGITS
    per
    0.10
    pery
    0.08
    kart
    0.08
    pen
    0.08
    erta
    0.08
    ting
    0.07
    /fl
    0.07
     flips
    0.07
    ¼
    0.07
    over
    0.07
    Activations Density 0.003%

    No Known Activations