© 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. 18824
    Prev
    Next
    INDEX
    Explanations

    positive descriptors and attributes related to characters and storylines

    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
    ŀæĢ§
    -0.07
    ساÙĨÛĮ
    -0.07
    çĤī
    -0.07
    BOOST
    -0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.07
    .Atomic
    -0.07
    raç
    -0.07
    ircuit
    -0.07
    ashboard
    -0.07
     пÑĥÑĤ
    -0.07
    POSITIVE LOGITS
    aan
    0.06
     PD
    0.06
     crush
    0.06
    daki
    0.06
     Crush
    0.06
    PD
    0.05
     Fernandez
    0.05
     handsome
    0.05
     chill
    0.05
     ê
    0.05
    Activations Density 0.009%

    No Known Activations