© 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. 3128
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations or named places

    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
    /editor
    -0.08
    çģ£
    -0.08
    heed
    -0.08
    еÑĢк
    -0.07
     Downtown
    -0.07
     downtown
    -0.07
    innen
    -0.07
    .records
    -0.07
     ÅŁeh
    -0.07
    .mongo
    -0.07
    POSITIVE LOGITS
     Connecticut
    0.08
     remote
    0.08
     Michigan
    0.08
     near
    0.07
     countryside
    0.07
     Georgia
    0.07
     rural
    0.07
     Ukraine
    0.07
     resort
    0.07
     Arkansas
    0.07
    Activations Density 0.038%

    No Known Activations