© 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. 118177
    Prev
    Next
    INDEX
    Explanations

    historical or political terms related to territories and governance

    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
    COPE
    -0.08
    olley
    -0.06
    coh
    -0.06
    oine
    -0.06
     ÑĢÑĥÑĩ
    -0.06
    PLIC
    -0.06
    ogue
    -0.06
    nar
    -0.06
    UBE
    -0.06
     editorial
    -0.06
    POSITIVE LOGITS
     administrative
    0.08
     province
    0.07
     county
    0.07
     استاÙĨ
    0.07
     Administrative
    0.07
     облаÑģÑĤи
    0.07
     prefect
    0.07
     окÑĢÑĥг
    0.07
    å·ŀ
    0.07
     administr
    0.07
    Activations Density 0.016%

    No Known Activations