© 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. 129376
    Prev
    Next
    INDEX
    Explanations

    phrases involving the act of shaking or expressing disbelief

    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
    kova
    -0.07
    PÅĻi
    -0.07
    xec
    -0.07
    ινÏĮ
    -0.07
    ions
    -0.07
    é¤
    -0.06
    folk
    -0.06
    ãĥªãĤ«
    -0.06
    kate
    -0.06
    ãĥ¼ãĥĦ
    -0.06
    POSITIVE LOGITS
     shake
    0.13
     shaking
    0.12
     shook
    0.11
     Shake
    0.11
     shakes
    0.11
    shake
    0.10
     shaken
    0.08
    oord
    0.07
    peare
    0.07
    stakes
    0.07
    Activations Density 0.011%

    No Known Activations