© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 39872
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or administrative divisions

    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
    fila
    -0.07
    /non
    -0.06
     deutschland
    -0.06
     Druh
    -0.06
     Mev
    -0.06
     æ´
    -0.06
     вÑĸÑĤ
    -0.06
    yun
    -0.06
    ιά
    -0.06
    olics
    -0.06
    POSITIVE LOGITS
    -level
    0.08
     boundaries
    0.08
    -wide
    0.08
    wide
    0.08
    /Area
    0.07
    份
    0.07
     lá»
    0.07
     boundary
    0.07
    -Level
    0.07
    /count
    0.07
    Activations Density 0.033%

    No Known Activations