© 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. 9-LLAMASCOPE-RES-131K
    11. 97586
    Prev
    Next
    INDEX
    Explanations

    specific numerical addresses and locations

    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
     particular
    -0.06
     news
    -0.06
    291
    -0.06
    -0.05
    520
    -0.05
    ful
    -0.05
    668
    -0.05
    lect
    -0.05
    ysl
    -0.05
    regor
    -0.05
    POSITIVE LOGITS
     aray
    0.09
     skoro
    0.08
    .scalablytyped
    0.07
    θÏħ
    0.07
    ICODE
    0.07
    \grid
    0.07
     moden
    0.07
    _submenu
    0.07
    .jd
    0.07
    emy
    0.07
    Activations Density 0.006%

    No Known Activations