© 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. 123937
    Prev
    Next
    INDEX
    Explanations

    references to specific TV shows and their elements

    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
    chant
    -0.07
    quare
    -0.07
    illion
    -0.06
    quot
    -0.06
    oni
    -0.06
    лÑĥж
    -0.06
    ilon
    -0.06
    anko
    -0.06
    arend
    -0.06
     bu
    -0.06
    POSITIVE LOGITS
    åIJ§
    0.08
     imagine
    0.08
     versus
    0.08
     notice
    0.08
     Notice
    0.07
    Notice
    0.07
    notice
    0.07
    CLUD
    0.07
     yourself
    0.06
     kurtul
    0.06
    Activations Density 0.050%

    No Known Activations