© 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. 5262
    Prev
    Next
    INDEX
    Explanations

    concepts related to localization and translation across multiple languages

    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
    VML
    -0.07
    ichier
    -0.07
    icket
    -0.06
    formats
    -0.06
    éĢĢ
    -0.06
    adera
    -0.06
    lys
    -0.06
    á»ĥ
    -0.06
    eras
    -0.06
    empo
    -0.06
    POSITIVE LOGITS
     localization
    0.08
    ASET
    0.07
    essler
    0.07
    val
    0.06
    æĬĺ
    0.06
    /*@
    0.06
    oton
    0.06
    bers
    0.06
     Localization
    0.06
    ربÛĮ
    0.06
    Activations Density 0.007%

    No Known Activations