© 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. 15-LLAMASCOPE-RES-131K
    11. 87701
    Prev
    Next
    INDEX
    Explanations

    concepts related to proposals, agreements, and changes in regulations or initiatives

    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
    oren
    -0.07
    amel
    -0.07
     же
    -0.07
    inis
    -0.06
    buch
    -0.06
     aber
    -0.06
    istrovstvÃŃ
    -0.06
    geber
    -0.06
    ango
    -0.05
    barang
    -0.05
    POSITIVE LOGITS
     recently
    0.08
    UBLE
    0.08
    cio
    0.07
    æĭľ
    0.07
     Vance
    0.07
    recent
    0.06
    Recent
    0.06
    Earlier
    0.06
    cus
    0.06
    UMP
    0.06
    Activations Density 0.048%

    No Known Activations