© 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 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. 3455
    Prev
    Next
    INDEX
    Explanations

    phrases related to business mergers and operational enhancements

    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
    essler
    -0.07
    abant
    -0.06
     mo
    -0.06
     sucker
    -0.05
     Fang
    -0.05
    bul
    -0.05
     basic
    -0.05
     unlike
    -0.05
    \modules
    -0.05
    orida
    -0.05
    POSITIVE LOGITS
     continue
    0.10
    æĽ´åĬł
    0.09
    continue
    0.09
     Continue
    0.09
    ãģķãĤīãģ«
    0.09
     further
    0.09
    ipay
    0.08
     continuation
    0.08
     continues
    0.08
    æĽ´
    0.08
    Activations Density 0.031%

    No Known Activations