© 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. 85007
    Prev
    Next
    INDEX
    Explanations

    references to cooking techniques and ingredients

    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
    jsc
    -0.07
     kriz
    -0.07
    azers
    -0.07
    menus
    -0.07
    _flip
    -0.07
     ÙħستÙĤ
    -0.07
     dek
    -0.06
    éī
    -0.06
    undy
    -0.06
     lần
    -0.06
    POSITIVE LOGITS
     grind
    0.10
     grinding
    0.09
     Grinding
    0.07
     blender
    0.07
     paste
    0.07
     mortar
    0.07
     Blender
    0.06
     pest
    0.06
     pand
    0.06
     grinder
    0.06
    Activations Density 0.097%

    No Known Activations