© 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. 30210
    Prev
    Next
    INDEX
    Explanations

    references to educational qualifications

    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
     nonzero
    -0.08
    .nz
    -0.07
     ëŁ
    -0.07
     Euros
    -0.07
     europ
    -0.06
    _fid
    -0.06
    Britain
    -0.06
    زÙħاÙĨ
    -0.06
     british
    -0.06
     euros
    -0.06
    POSITIVE LOGITS
     US
    0.21
     USA
    0.19
    USA
    0.17
     American
    0.16
    US
    0.16
    ç¾İåĽ½
    0.15
     ç¾İåĽ½
    0.15
    American
    0.14
     America
    0.14
     СШÐIJ
    0.14
    Activations Density 0.578%

    No Known Activations