© 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. 54152
    Prev
    Next
    INDEX
    Explanations

    references to translation and translators in literary contexts

    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
     ref
    -0.06
    loquent
    -0.06
    chter
    -0.06
    alborg
    -0.06
    лова
    -0.06
    uD
    -0.06
    leans
    -0.06
    acial
    -0.06
    inem
    -0.06
    etri
    -0.05
    POSITIVE LOGITS
     translators
    0.09
     translation
    0.09
     translations
    0.09
     translator
    0.09
    translations
    0.08
     ç¿
    0.08
     Translator
    0.08
    -trans
    0.08
    ç¿»
    0.08
     Translation
    0.08
    Activations Density 0.012%

    No Known Activations