© 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. 85518
    Prev
    Next
    INDEX
    Explanations

    concepts related to user experience and interaction with technology

    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
    warf
    -0.06
    gnore
    -0.06
    kil
    -0.06
    LAG
    -0.06
    gba
    -0.06
     Wenger
    -0.05
    _testing
    -0.05
    _flush
    -0.05
     sustainable
    -0.05
     kil
    -0.05
    POSITIVE LOGITS
     productivity
    0.09
    çĶŁæ´»
    0.09
     daily
    0.08
     everyday
    0.08
    oldt
    0.08
    daily
    0.08
    orgh
    0.07
    ewan
    0.07
     quotid
    0.07
    conc
    0.07
    Activations Density 0.024%

    No Known Activations