© 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. 107804
    Prev
    Next
    INDEX
    Explanations

    references to voter turnout statistics and related data

    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
    eya
    -0.09
    .scalablytyped
    -0.08
     scand
    -0.08
    earn
    -0.07
    eras
    -0.07
    íıī
    -0.07
    agina
    -0.07
    owi
    -0.07
    ÙĦس
    -0.06
     Karlov
    -0.06
    POSITIVE LOGITS
     early
    0.08
     already
    0.07
     processed
    0.07
    人人
    0.07
     progress
    0.06
     yet
    0.06
     compared
    0.06
    å°ļ
    0.06
     demand
    0.06
     Early
    0.06
    Activations Density 0.015%

    No Known Activations