© 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. 78411
    Prev
    Next
    INDEX
    Explanations

    references to Java Enterprise Beans and related programming constructs

    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
    ASI
    -0.08
    fte
    -0.07
    acks
    -0.07
     gelen
    -0.07
    ents
    -0.07
    .Path
    -0.07
    cctor
    -0.07
    OUCH
    -0.07
    OLOR
    -0.07
    aries
    -0.06
    POSITIVE LOGITS
    ify
    0.06
    ified
    0.06
    ureka
    0.06
    309
    0.06
    vers
    0.06
    ID
    0.06
    iedade
    0.06
    .getBean
    0.05
    293
    0.05
     Hundred
    0.05
    Activations Density 0.003%

    No Known Activations