© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53962
    Prev
    Next
    INDEX
    Explanations

    titles or references to specific TV episodes or shows

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ä¿
    -0.07
     phái
    -0.06
     FAIL
    -0.06
    ÅĻÃŃž
    -0.06
     patched
    -0.06
    اÙĦÙĩ
    -0.06
    _generated
    -0.06
    //---------------------------------------------------------------------------↵↵
    -0.06
    uries
    -0.06
    æŃ©
    -0.06
    POSITIVE LOGITS
     episode
    0.18
     Episode
    0.15
    episode
    0.14
     episodes
    0.13
    Episode
    0.12
     guest
    0.11
    isode
    0.10
     Episodes
    0.09
    _episode
    0.09
     eps
    0.08
    Activations Density 0.117%

    No Known Activations