© 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. 120178
    Prev
    Next
    INDEX
    Explanations

    key elements and actions related to research initiatives and organizational support for various objectives

    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
    chter
    -0.08
    mé
    -0.07
    PRS
    -0.07
    kowski
    -0.07
    ئت
    -0.07
    aign
    -0.07
    ئ
    -0.07
    stub
    -0.07
    hue
    -0.07
    fon
    -0.06
    POSITIVE LOGITS
    ingham
    0.06
     altogether
    0.06
    oved
    0.06
    ูà¸Ĺ
    0.06
     mutual
    0.06
     hol
    0.06
    aset
    0.05
     Bradley
    0.05
    olders
    0.05
     CoreData
    0.05
    Activations Density 0.062%

    No Known Activations