© 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. 9-LLAMASCOPE-RES-131K
    11. 95194
    Prev
    Next
    INDEX
    Explanations

    measurements and specifications related to products

    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
     according
    -0.06
     mod
    -0.06
     trace
    -0.05
     phenomenon
    -0.05
     far
    -0.05
     ac
    -0.05
     phenomena
    -0.05
     Federation
    -0.05
     context
    -0.05
     contrary
    -0.05
    POSITIVE LOGITS
     aio
    0.07
    okoj
    0.07
     Äijâu
    0.07
    ebb
    0.07
    imler
    0.07
    .small
    0.07
    .adv
    0.07
     nhá»ı
    0.07
    eria
    0.07
    ementia
    0.07
    Activations Density 0.008%

    No Known Activations