© 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. 30825
    Prev
    Next
    INDEX
    Explanations

    references to work-related situations and challenges

    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
    evi
    -0.07
    VERR
    -0.07
    addock
    -0.06
     indem
    -0.06
    ĩĮ
    -0.06
     Pros
    -0.06
     gen
    -0.05
     Kendrick
    -0.05
    jan
    -0.05
    ืà¸Ļ
    -0.05
    POSITIVE LOGITS
     during
    0.09
    æľŁéĹ´
    0.08
    during
    0.07
     ÑĤогда
    0.07
     ÑĤодÑĸ
    0.07
    å½ĵ
    0.07
    à¸Ĥà¸ĵะ
    0.07
     ëĭ¹ìĭľ
    0.07
     durante
    0.07
    ìĿ¼ìĹIJ
    0.07
    Activations Density 0.048%

    No Known Activations