© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82625
    Prev
    Next
    INDEX
    Explanations

    whimsical or playful language related to food and fantastical themes

    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
    uplicates
    -0.08
    ãģ®ãģ¿
    -0.08
    ultan
    -0.08
    cedes
    -0.08
    à¥Ģय
    -0.07
    ISTRIBUT
    -0.07
    ãģĦãĤĭ
    -0.07
    ãģ¨ãģĨ
    -0.07
    ÑĩеÑģки
    -0.07
    ytt
    -0.07
    POSITIVE LOGITS
    ery
    0.12
    ie
    0.12
    iez
    0.09
    keepers
    0.09
    keeper
    0.09
    ies
    0.08
    ÑģÑı
    0.08
    igans
    0.08
    ish
    0.08
    eries
    0.07
    Activations Density 0.058%

    No Known Activations