© 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. 15-LLAMASCOPE-RES-131K
    11. 89013
    Prev
    Next
    INDEX
    Explanations

    suffixes typically associated with geographical locations or demonyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The suffix "-ia" (and variations like "-ania", "-onia") at the end of words, typically used to form place names, countries, regions, or proper nouns with Latin-derived naming conventions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ngo
    -0.08
    ÃŃa
    -0.07
    ÃŃas
    -0.07
    aroo
    -0.07
    ish
    -0.07
    illez
    -0.07
    cover
    -0.07
    thing
    -0.07
    ÑģÑı
    -0.07
    unga
    -0.07
    POSITIVE LOGITS
    ity
    0.10
    zelf
    0.09
    acl
    0.09
    ะ
    0.09
    xis
    0.09
    y
    0.08
    ele
    0.08
    cy
    0.08
    gle
    0.08
    yen
    0.07
    Activations Density 0.135%

    No Known Activations