© 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. 119641
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thinking"

    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
    Ñĩе
    -0.08
    eft
    -0.08
    asaki
    -0.08
    orsi
    -0.07
    StateChanged
    -0.07
    dere
    -0.07
    sov
    -0.07
    lya
    -0.07
    leo
    -0.07
    UserCode
    -0.07
    POSITIVE LOGITS
     maybe
    0.07
    atics
    0.06
     exposures
    0.06
    念
    0.06
     Fried
    0.06
    etic
    0.06
     worst
    0.06
    maybe
    0.06
     perhaps
    0.06
    andom
    0.05
    Activations Density 0.005%

    No Known Activations