© 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. 61894
    Prev
    Next
    INDEX
    Explanations

    terms that denote critical roles or essential parts within a system or process

    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
     Kendrick
    -0.07
     Weaver
    -0.07
     Erotik
    -0.06
    γκ
    -0.06
    _empresa
    -0.06
    zell
    -0.06
     >č↵
    -0.06
    DataContract
    -0.06
    avit
    -0.06
     몰
    -0.06
    POSITIVE LOGITS
     Hak
    0.07
    elps
    0.06
     toward
    0.06
    jdbc
    0.06
     along
    0.06
    imetype
    0.06
    443
    0.06
    ÑĭÑĤ
    0.06
     Rif
    0.06
     Aires
    0.06
    Activations Density 0.020%

    No Known Activations