© 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. 22-LLAMASCOPE-RES-131K
    11. 3918
    Prev
    Next
    INDEX
    Explanations

    interactions involving questioning and explanation processes

    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
    нин
    -0.07
    oto
    -0.07
    OTO
    -0.06
    verbatim
    -0.06
    .EventQueue
    -0.06
    jez
    -0.06
    åĤ¬
    -0.06
    keh
    -0.06
    ishlist
    -0.06
    нина
    -0.06
    POSITIVE LOGITS
     explanation
    0.38
     explanations
    0.35
     explain
    0.35
     explaining
    0.32
     explained
    0.32
     Explanation
    0.31
     explains
    0.31
     Explain
    0.28
    Explanation
    0.28
    explained
    0.28
    Activations Density 0.101%

    No Known Activations