© 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. 54923
    Prev
    Next
    INDEX
    Explanations

    elements related to user authentication and database structures

    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
     ãĤ±
    -0.08
    еÑĢалÑĮ
    -0.07
     ç§ĭ
    -0.07
     nackt
    -0.07
    mask
    -0.07
    .bukkit
    -0.07
    638
    -0.07
    .Localization
    -0.07
    azor
    -0.07
    Ú©Ùĩ
    -0.07
    POSITIVE LOGITS
     Overnight
    0.06
     Institutes
    0.06
    een
    0.06
    iyor
    0.05
    retch
    0.05
    borough
    0.05
    idar
    0.05
    bes
    0.05
    .Framework
    0.05
    HI
    0.05
    Activations Density 0.006%

    No Known Activations