© 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. 124750
    Prev
    Next
    INDEX
    Explanations

    references to traditional Greek theater and drama

    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
    Å¡ak
    -0.08
    Ç
    -0.08
    à¥ĭà¤Ĥ,
    -0.07
    ãĥķãĤ
    -0.07
    rosso
    -0.07
     videog
    -0.07
    адж
    -0.07
    ô
    -0.07
    ëŁŃ
    -0.07
     <<-
    -0.07
    POSITIVE LOGITS
     Uncategorized
    0.08
    âĢIJ
    0.06
     WIFI
    0.06
     Colour
    0.06
    ?↵
    0.06
    rowsable
    0.06
    "path
    0.06
    Ø©
    0.06
    alim
    0.06
    /stdc
    0.06
    Activations Density 0.024%

    No Known Activations