© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2923
    Prev
    Next
    INDEX
    Explanations

    Java import statements, particularly those related to utility classes

    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
    127
    -0.07
    gere
    -0.07
    iej
    -0.07
    545
    -0.06
     chim
    -0.06
    NewLabel
    -0.06
    udoku
    -0.06
    .createObject
    -0.06
    ibaba
    -0.06
    etto
    -0.06
    POSITIVE LOGITS
    ippy
    0.07
    redient
    0.06
    .getRuntime
    0.06
    usercontent
    0.06
    кÑĤÑĥ
    0.06
    Inputs
    0.06
     Inputs
    0.06
     inputs
    0.06
    .fun
    0.06
     functor
    0.06
    Activations Density 0.000%

    No Known Activations