© 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. 4367
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comparisons or descriptions of products in the technology and gadget market

    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
    untas
    -0.07
    apons
    -0.07
    .WinForms
    -0.06
    ÙĦÙĤ
    -0.06
    dsn
    -0.06
     ------------------------------------------------------------------------↵
    -0.06
     soud
    -0.06
     è¶
    -0.06
    skou
    -0.06
    posables
    -0.06
    POSITIVE LOGITS
     genre
    0.09
     category
    0.08
     possession
    0.06
     eins
    0.06
    genre
    0.06
     genres
    0.06
    avian
    0.06
    INGER
    0.06
     field
    0.06
     categories
    0.06
    Activations Density 0.021%

    No Known Activations