© 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. 61741
    Prev
    Next
    INDEX
    Explanations

    terms related to user interactions and engagement

    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
    æīį
    -0.07
     Tham
    -0.06
     Chance
    -0.06
    rame
    -0.06
    dens
    -0.06
    atom
    -0.06
     gradu
    -0.05
    anium
    -0.05
    Chance
    -0.05
    اÙħÛĮÙĨ
    -0.05
    POSITIVE LOGITS
    æĺĵ
    0.11
     easy
    0.10
     fácil
    0.10
     easily
    0.09
    easy
    0.09
     kolay
    0.09
    Easy
    0.09
     dÃłng
    0.09
     Easily
    0.09
     compared
    0.09
    Activations Density 0.062%

    No Known Activations