© 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. 29174
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a sense of obligation or purpose

    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
    itas
    -0.06
    eld
    -0.06
    raph
    -0.06
    ảy
    -0.06
    clusions
    -0.06
    edin
    -0.06
    ima
    -0.06
    rompt
    -0.06
    arsity
    -0.06
    lessly
    -0.06
    POSITIVE LOGITS
    unately
    0.10
     instance
    0.10
    bid
    0.09
     example
    0.08
    give
    0.07
    zier
    0.07
    given
    0.07
    hiba
    0.07
    instance
    0.06
    geo
    0.06
    Activations Density 0.032%

    No Known Activations