© 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. 56635
    Prev
    Next
    INDEX
    Explanations

    syntax related to programming 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
    resh
    -0.07
     Leader
    -0.07
    ÑĢоÑĤ
    -0.07
    .Abstractions
    -0.07
    eper
    -0.07
    Leader
    -0.07
    _FOREACH
    -0.06
    .IsAny
    -0.06
    forums
    -0.06
    zier
    -0.06
    POSITIVE LOGITS
     plugins
    0.07
     Plugins
    0.06
    ijn
    0.06
     Saunders
    0.06
     PIE
    0.06
    ç¥Ń
    0.06
    Plugins
    0.06
     UIBar
    0.06
     pie
    0.06
    æĪIJ人
    0.06
    Activations Density 0.006%

    No Known Activations