© 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. 72457
    Prev
    Next
    INDEX
    Explanations

    second-person pronouns, indicating direct address to the reader

    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
    áf
    -0.07
    ISTA
    -0.06
     Gand
    -0.06
    ÌĨ
    -0.06
    ungan
    -0.06
    uard
    -0.06
    bjerg
    -0.06
     Lon
    -0.05
    probably
    -0.05
     probably
    -0.05
    POSITIVE LOGITS
     varsa
    0.08
    è¿Ļæł·
    0.08
    éĤ£æł·
    0.07
    647
    0.07
     hadn
    0.07
    olit
    0.07
    æľīä»Ģä¹Ī
    0.07
     اÙĦØŃÙĬ
    0.07
    763
    0.07
     sudden
    0.07
    Activations Density 0.035%

    No Known Activations