© 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. 14273
    Prev
    Next
    INDEX
    Explanations

    information related to television show renewals and seasons

    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
    azer
    -0.07
    lesai
    -0.07
    ilder
    -0.07
    elah
    -0.07
    etim
    -0.07
    IEWS
    -0.06
    etooth
    -0.06
    idis
    -0.06
    urovision
    -0.06
    íĥĦ
    -0.06
    POSITIVE LOGITS
     additional
    0.08
     another
    0.08
    additional
    0.08
     continuation
    0.08
    another
    0.07
     continue
    0.07
     further
    0.07
    继ç»Ń
    0.07
     Kaw
    0.07
     continu
    0.07
    Activations Density 0.004%

    No Known Activations