© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 39759
    Prev
    Next
    INDEX
    Explanations

    references to individuals significantly contributing to their communities or professions

    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
     such
    -0.07
    :
    -0.06
     eg
    -0.06
     blind
    -0.06
    bir
    -0.06
    out
    -0.06
     breakthrough
    -0.06
    such
    -0.06
     Martins
    -0.05
    áº
    -0.05
    POSITIVE LOGITS
     Fav
    0.07
    ONGL
    0.07
    ANNEL
    0.07
    inge
    0.07
    'gc
    0.07
     hepsi
    0.07
    SetActive
    0.07
    nock
    0.07
    à¸Ħรà¸ļ
    0.07
    Touches
    0.07
    Activations Density 0.057%

    No Known Activations