© 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 EvalsExportsAPI 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. 57522
    Prev
    Next
    INDEX
    Explanations

    columns and attributes related to data structures or tables

    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
     Princip
    -0.06
    estring
    -0.06
     tur
    -0.06
    ANNEL
    -0.06
     Limited
    -0.06
    enko
    -0.06
    annel
    -0.05
    arte
    -0.05
     Tur
    -0.05
    úsqueda
    -0.05
    POSITIVE LOGITS
    iye
    0.07
    £
    0.07
    squeeze
    0.07
    .scalablytyped
    0.06
    .updateDynamic
    0.06
    oup
    0.06
     Mig
    0.06
    ê¹Ģ
    0.06
     taraf
    0.06
    _fsm
    0.06
    Activations Density 0.000%

    No Known Activations