© 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. 17-LLAMASCOPE-RES-131K
    11. 81964
    Prev
    Next
    INDEX
    Explanations

    references to financial figures, particularly those involving millions and billions of dollars

    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
    ou
    -0.06
    eli
    -0.06
    nak
    -0.06
    bye
    -0.06
    iz
    -0.06
     ranks
    -0.06
    Ãł
    -0.06
    516
    -0.06
     rank
    -0.06
     saturn
    -0.06
    POSITIVE LOGITS
    haf
    0.07
     è®
    0.07
    aires
    0.07
    unded
    0.06
    SENS
    0.06
    apia
    0.06
    abytes
    0.06
    ÃŃch
    0.06
    .pretty
    0.06
    edBy
    0.06
    Activations Density 0.009%

    No Known Activations