© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15998
    Prev
    Next
    INDEX
    Explanations

    references to significant projects or developments in infrastructure

    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
    ichel
    -0.08
    ÑħÑĸд
    -0.07
    IOS
    -0.06
    รà¸ĵ
    -0.06
    aticon
    -0.06
    æ¡£
    -0.06
    باز
    -0.06
    .Solid
    -0.06
    γγÏģαÏĨ
    -0.06
    .Layer
    -0.06
    POSITIVE LOGITS
     successfully
    0.10
     yesterday
    0.09
     Successfully
    0.08
    successfully
    0.07
     inaugural
    0.07
     completed
    0.07
     recently
    0.07
     Yesterday
    0.07
     Successful
    0.07
     succesfully
    0.07
    Activations Density 0.076%

    No Known Activations