© 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. 126633
    Prev
    Next
    INDEX
    Explanations

    communication-related technical terms and concepts

    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
    egg
    -0.06
     Investor
    -0.06
    .usermodel
    -0.06
    erno
    -0.06
    strap
    -0.06
    arch
    -0.06
     Dann
    -0.05
     perfection
    -0.05
     Prescott
    -0.05
    geh
    -0.05
    POSITIVE LOGITS
    .opendaylight
    0.07
    à¹īà¸ĩ
    0.07
    .yang
    0.07
    ť
    0.07
    itemap
    0.07
    neider
    0.07
    .appspot
    0.07
     bach
    0.07
    fabric
    0.07
    lsa
    0.07
    Activations Density 0.007%

    No Known Activations