© 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. 117734
    Prev
    Next
    INDEX
    Explanations

    phrases related to promotional events and contests for purchasing items

    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
     very
    -0.06
    meden
    -0.06
     too
    -0.06
    ardon
    -0.06
     sometimes
    -0.06
     much
    -0.06
     readily
    -0.06
     as
    -0.06
    clone
    -0.06
     perhaps
    -0.06
    POSITIVE LOGITS
     EITHER
    0.09
     ANY
    0.09
    (any
    0.08
     anytime
    0.08
     bất
    0.08
     anywhere
    0.07
     زاد
    0.07
     hoặc
    0.07
    .IsAny
    0.07
    any
    0.07
    Activations Density 0.025%

    No Known Activations