© 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. 95767
    Prev
    Next
    INDEX
    Explanations

    news-related terminology and references to organizations or concepts in the media industry

    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
    coc
    -0.07
    ONTAL
    -0.07
    acas
    -0.07
    Ñģм
    -0.07
    afari
    -0.07
    CELER
    -0.07
     McCorm
    -0.07
    EFF
    -0.06
     Blond
    -0.06
    ÏĦοÏħ
    -0.06
    POSITIVE LOGITS
    swire
    0.07
     entr
    0.07
     global
    0.06
     é£
    0.06
     Macro
    0.06
     bas
    0.06
    ru
    0.06
     glob
    0.06
    _FT
    0.06
    rade
    0.06
    Activations Density 0.001%

    No Known Activations