© 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. 39693
    Prev
    Next
    INDEX
    Explanations

    references and sections in academic texts

    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
    ãn
    -0.06
    pling
    -0.06
    .persist
    -0.06
    aga
    -0.06
    plug
    -0.05
    ixon
    -0.05
    htm
    -0.05
     Dry
    -0.05
     dict
    -0.05
    recogn
    -0.05
    POSITIVE LOGITS
     preferredStyle
    0.07
    elsing
    0.07
    -background
    0.07
    .scalablytyped
    0.07
    MeasureSpec
    0.07
    awy
    0.07
    ervoir
    0.06
    æĸĻ
    0.06
    å¯Ĩ
    0.06
    ardown
    0.06
    Activations Density 0.008%

    No Known Activations