© 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. 15-LLAMASCOPE-RES-131K
    11. 27399
    Prev
    Next
    INDEX
    Explanations

    patterns of variation and transformation in objects or situations

    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
    immel
    -0.09
     prematurely
    -0.07
    kees
    -0.07
     ç¢
    -0.07
    ERV
    -0.06
     mapDispatchToProps
    -0.06
    à¹īà¸Ļ
    -0.06
    chant
    -0.06
    aira
    -0.06
    kea
    -0.06
    POSITIVE LOGITS
     changing
    0.13
     Changing
    0.12
     switching
    0.12
    -changing
    0.11
    changing
    0.11
    Changing
    0.10
     switched
    0.10
     switch
    0.10
     Switch
    0.10
    switch
    0.10
    Activations Density 0.167%

    No Known Activations