© 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. 88218
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to impoverished urban areas and refugee situations

    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
    zell
    -0.08
    çĽĹ
    -0.07
    ulk
    -0.07
    idl
    -0.07
     Slate
    -0.06
    ksam
    -0.06
    rieb
    -0.06
    ÑģилÑĮ
    -0.06
     zev
    -0.06
    ibel
    -0.06
    POSITIVE LOGITS
     dwell
    0.10
     area
    0.07
     dwelling
    0.06
     Watts
    0.06
    lr
    0.06
    éĩĮçļĦ
    0.06
    ÙĨØ´
    0.06
     housing
    0.06
     areas
    0.06
    bers
    0.06
    Activations Density 0.017%

    No Known Activations