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

    Neuronpedia

    Jacobian LensNEW
    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. 75045
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty and change

    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
    å·
    -0.06
    391
    -0.06
    strict
    -0.06
    359
    -0.06
    opoly
    -0.06
    enci
    -0.06
    TK
    -0.06
    .operations
    -0.06
    marks
    -0.06
    æĶ
    -0.05
    POSITIVE LOGITS
     predictable
    0.09
     certainty
    0.08
     cert
    0.07
    roker
    0.07
    Sure
    0.07
     guaranteed
    0.07
     Sure
    0.07
     Schwarz
    0.07
    iesel
    0.07
     inev
    0.07
    Activations Density 0.005%

    No Known Activations