© 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. 125572
    Prev
    Next
    INDEX
    Explanations

    references to changes or renovations in movie theaters

    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
    iggins
    -0.07
    vig
    -0.07
    gency
    -0.06
    oubted
    -0.06
    azar
    -0.06
    iÄħ
    -0.06
    kontakte
    -0.06
    åĬ¨çĶŁæĪIJ
    -0.06
     penal
    -0.06
    Ware
    -0.06
    POSITIVE LOGITS
     Wet
    0.07
    UGC
    0.07
    à¸Ħรà¸ļ
    0.06
    ilos
    0.06
     hå
    0.06
    à¸ł
    0.06
    930
    0.06
     Movies
    0.06
     Picture
    0.06
    116
    0.06
    Activations Density 0.011%

    No Known Activations