© 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. 84288
    Prev
    Next
    INDEX
    Explanations

    references to banks and banking institutions

    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
    alamat
    -0.08
    luvÃŃ
    -0.08
    imli
    -0.07
    ncy
    -0.07
    ilet
    -0.07
    onest
    -0.07
    .Foundation
    -0.07
    trie
    -0.07
    incerely
    -0.07
    glas
    -0.06
    POSITIVE LOGITS
     Sons
    0.06
     Chase
    0.06
    óm
    0.06
    airs
    0.06
    ruptcy
    0.06
     Bo
    0.05
    A
    0.05
     Ravens
    0.05
    ['__
    0.05
    wide
    0.05
    Activations Density 0.003%

    No Known Activations