© 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. 95214
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "ride" and related terms in the context of transportation

    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
    xing
    -0.09
    otate
    -0.08
    loe
    -0.08
    /right
    -0.08
    mente
    -0.07
    landers
    -0.07
    rient
    -0.07
    ayed
    -0.07
    adolu
    -0.07
    ted
    -0.07
    POSITIVE LOGITS
    oux
    0.07
    /dr
    0.07
    out
    0.06
    alin
    0.06
    awn
    0.06
    ouser
    0.06
     Peg
    0.06
    LER
    0.06
    hare
    0.06
    boss
    0.06
    Activations Density 0.011%

    No Known Activations