© 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. 40887
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to cooking and food preparation

    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
    .trim
    -0.06
     spray
    -0.06
     spraying
    -0.05
    chai
    -0.05
     practice
    -0.05
    phinx
    -0.05
    woo
    -0.05
     зд
    -0.05
     Palmer
    -0.05
    .github
    -0.05
    POSITIVE LOGITS
    imuth
    0.08
    ptrdiff
    0.07
    unctuation
    0.07
    _PROVID
    0.07
    ople
    0.07
    orem
    0.07
    FullYear
    0.07
    kaç
    0.07
    ÑģÑĸм
    0.07
    chedulers
    0.06
    Activations Density 0.013%

    No Known Activations