© 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. 88079
    Prev
    Next
    INDEX
    Explanations

    references to videos and hands-on activities related to building and creating projects

    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
    bÃŃ
    -0.07
    orelease
    -0.07
    asurer
    -0.07
    istrovstvÃŃ
    -0.07
    zion
    -0.07
    ropol
    -0.07
    .GetObject
    -0.07
    λεκ
    -0.07
    /options
    -0.07
    polator
    -0.07
    POSITIVE LOGITS
     EITHER
    0.08
    819
    0.07
     preferably
    0.07
     pairs
    0.06
     complete
    0.06
     imaginary
    0.06
    aut
    0.06
    mini
    0.06
     either
    0.06
    aware
    0.06
    Activations Density 0.017%

    No Known Activations