© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97621
    Prev
    Next
    INDEX
    Explanations

    words related to loan applications and the application process

    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
    hausen
    -0.07
     pockets
    -0.06
    à¸ĵ
    -0.06
    bal
    -0.06
    ouve
    -0.06
    ialect
    -0.06
     deep
    -0.06
     Bag
    -0.06
     bag
    -0.06
    ptal
    -0.05
    POSITIVE LOGITS
    .gov
    0.07
    heed
    0.07
    ailer
    0.07
    리카
    0.07
    enan
    0.07
    icer
    0.07
     pÅĤ
    0.07
    longleftrightarrow
    0.07
    indr
    0.07
     ë§Īë²ķ
    0.06
    Activations Density 0.001%

    No Known Activations