© 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. 81278
    Prev
    Next
    INDEX
    Explanations

    expressions of praise and congratulatory remarks

    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
    raci
    -0.07
    .onViewCreated
    -0.07
    imei
    -0.07
    Å¡tÃŃ
    -0.07
    cheid
    -0.07
    پس
    -0.07
    Å¡il
    -0.07
    AdapterManager
    -0.07
    iosper
    -0.07
    erez
    -0.06
    POSITIVE LOGITS
    ysz
    0.07
     effort
    0.06
     efforts
    0.06
     overall
    0.06
     yourself
    0.06
     everyone
    0.06
     indeed
    0.06
    egers
    0.06
    ale
    0.06
    ÑijÑĢ
    0.05
    Activations Density 0.007%

    No Known Activations