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

    Neuronpedia

    Jacobian LensNEW
    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. 56172
    Prev
    Next
    INDEX
    Explanations

    references to financial matters and consumer products

    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
     rumor
    -0.07
    oppel
    -0.06
    ÂĢÂ
    -0.06
    mond
    -0.06
     rumors
    -0.06
     cass
    -0.06
     rumored
    -0.06
     favor
    -0.06
    .emf
    -0.06
    ãĥ³ãĤ¿
    -0.06
    POSITIVE LOGITS
     Wright
    0.07
    WithContext
    0.07
    .visual
    0.06
     civic
    0.06
    DL
    0.06
    uby
    0.06
     Laboratories
    0.06
    .community
    0.06
    inar
    0.06
    Ãļ
    0.06
    Activations Density 0.003%

    No Known Activations