© 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. 88959
    Prev
    Next
    INDEX
    Explanations

    comparative phrases relating to similarities and values

    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
    ica
    -0.07
     Ing
    -0.07
    Ïģα
    -0.07
    zell
    -0.07
    vla
    -0.07
    볨
    -0.06
    ÐĬ
    -0.06
    icer
    -0.06
    urope
    -0.06
    Ing
    -0.06
    POSITIVE LOGITS
    657
    0.06
     other
    0.06
    .asm
    0.06
    795
    0.06
    ãģĿãģ®ä»ĸ
    0.06
    à¸ķà¸Ļ
    0.06
    alara
    0.06
    formance
    0.05
    ccount
    0.05
    ä¹ĭä¸Ģ
    0.05
    Activations Density 0.020%

    No Known Activations