Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43512
    Prev
    Next
    INDEX
    Explanations

    cooking and preparation instructions in recipes

    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
    dera
    -0.08
    .scalablytyped
    -0.07
    omore
    -0.07
    emey
    -0.06
    clc
    -0.06
    uger
    -0.06
    teki
    -0.06
    Äįin
    -0.06
    alc
    -0.06
    Done
    -0.06
    POSITIVE LOGITS
     Arrange
    0.10
     Meanwhile
    0.10
    Meanwhile
    0.09
     Brush
    0.09
     Combine
    0.09
     Working
    0.09
     arrange
    0.08
    Arrange
    0.08
     Hal
    0.08
     Thread
    0.08
    Activations Density 0.089%

    No Known Activations