© 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. 57853
    Prev
    Next
    INDEX
    Explanations

    expressions related to beliefs and thoughts

    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
    Coder
    -0.08
    recht
    -0.07
    coni
    -0.07
     å¥
    -0.07
    age
    -0.07
    kker
    -0.07
    ugi
    -0.06
    ucas
    -0.06
    벤íĬ¸
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
     given
    0.08
    given
    0.07
     Given
    0.06
    _given
    0.06
    ible
    0.06
    ÑĪи
    0.05
     Upon
    0.05
    ulumi
    0.05
     Tod
    0.05
    SYNC
    0.05
    Activations Density 0.005%

    No Known Activations