© 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. 17-LLAMASCOPE-RES-131K
    11. 78876
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and events in Alabama

    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
     Portland
    -0.10
    Portland
    -0.10
     Oregon
    -0.10
    Oregon
    -0.08
     onCreateView
    -0.08
     Cornell
    -0.08
     Rochester
    -0.08
    hattan
    -0.07
    udit
    -0.07
    Minnesota
    -0.07
    POSITIVE LOGITS
     Alabama
    0.20
     Birmingham
    0.20
    Alabama
    0.19
    irmingham
    0.12
    abama
    0.10
     Iraqi
    0.10
     Mississippi
    0.10
     Auburn
    0.10
     Baghdad
    0.09
     Midlands
    0.09
    Activations Density 0.050%

    No Known Activations