© 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. 72904
    Prev
    Next
    INDEX
    Explanations

    phrases indicating foundational concepts or principles

    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
    GP
    -0.07
     tid
    -0.06
     extras
    -0.06
    vit
    -0.06
    rint
    -0.06
    èĩ³
    -0.06
    amar
    -0.06
     bit
    -0.06
    mant
    -0.06
    usch
    -0.06
    POSITIVE LOGITS
     upon
    0.11
    upon
    0.10
    nard
    0.09
     Upon
    0.08
    Upon
    0.08
    æĸ¼
    0.07
    avors
    0.07
     premises
    0.07
    247
    0.07
    UGIN
    0.07
    Activations Density 0.021%

    No Known Activations