© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 54591
    Prev
    Next
    INDEX
    Explanations

    programming commands and elements related to data structures or UI layouts

    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
    amarin
    -0.07
    rez
    -0.06
    atom
    -0.06
    vál
    -0.06
    olem
    -0.06
    akte
    -0.06
    enberg
    -0.06
     Bing
    -0.06
    RFC
    -0.06
     base
    -0.06
    POSITIVE LOGITS
    .gridx
    0.07
     Spicer
    0.07
     GridBagConstraints
    0.07
    undry
    0.07
    rones
    0.07
    Alignment
    0.07
    Spacer
    0.06
    _alignment
    0.06
     colspan
    0.06
    èµĸ
    0.06
    Activations Density 0.002%

    No Known Activations