© 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. 77627
    Prev
    Next
    INDEX
    Explanations

    URL path patterns and specific rewrite rules in configuration files

    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
    baum
    -0.07
    bilt
    -0.06
    arters
    -0.06
    .EntityFramework
    -0.06
    isNew
    -0.06
     mình
    -0.06
    nofollow
    -0.06
    reira
    -0.06
    sdale
    -0.06
    SION
    -0.06
    POSITIVE LOGITS
    ahr
    0.07
    s
    0.07
    bin
    0.07
    argin
    0.06
    adata
    0.06
    argar
    0.06
    bos
    0.06
    bben
    0.06
    EA
    0.06
    akh
    0.06
    Activations Density 0.005%

    No Known Activations