© 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. 74272
    Prev
    Next
    INDEX
    Explanations

    references to Java development environments and related configurations

    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
    reu
    -0.07
    mue
    -0.07
    pha
    -0.07
    ÑĨÑı
    -0.07
    dain
    -0.07
    amon
    -0.07
    aign
    -0.07
    igham
    -0.07
    haps
    -0.07
     euch
    -0.07
    POSITIVE LOGITS
     Holl
    0.07
    LPARAM
    0.06
     ETA
    0.06
     offsetof
    0.06
     sh
    0.06
     Taj
    0.06
     prompt
    0.06
    ëł¹
    0.06
     Bash
    0.06
    اذ
    0.06
    Activations Density 0.001%

    No Known Activations