© 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 EvalsExportsinterp-engineNEWAPI 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. 54311
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty and conditions related to potential outcomes

    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
    ork
    -0.07
    iesz
    -0.07
    ello
    -0.07
    ento
    -0.06
    rende
    -0.06
     coron
    -0.06
    zon
    -0.06
    stin
    -0.06
    iles
    -0.06
     ked
    -0.06
    POSITIVE LOGITS
    gan
    0.07
     actually
    0.07
    ÙĪØ·
    0.07
     Doing
    0.07
    oni
    0.07
    OTS
    0.07
    scoped
    0.07
     SHOULD
    0.06
    IAS
    0.06
    did
    0.06
    Activations Density 0.068%

    No Known Activations