© 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. 95291
    Prev
    Next
    INDEX
    Explanations

    complex words and phrases in multiple languages

    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
     who
    -0.07
    AGON
    -0.06
     Sink
    -0.06
     αÏħÏĦή
    -0.06
    ioned
    -0.06
     herself
    -0.05
    ÑĸлÑĮ
    -0.05
     whom
    -0.05
    lich
    -0.05
    ’d
    -0.05
    POSITIVE LOGITS
     itself
    0.13
     αÏħÏĦά
    0.10
     должно
    0.10
     коÑĤоÑĢое
    0.09
     Ñıке
    0.08
     Cristiano
    0.07
    ÑĤив
    0.07
     koje
    0.07
    ónico
    0.07
    .SDK
    0.07
    Activations Density 0.086%

    No Known Activations