© 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. 60490
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic areas or regions

    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
     Hayward
    -0.07
    yu
    -0.06
    PMC
    -0.06
    ober
    -0.06
    μαÏĦα
    -0.06
    wards
    -0.06
    iri
    -0.06
    thr
    -0.06
     Kelley
    -0.06
    ?a
    -0.06
    POSITIVE LOGITS
    arshal
    0.08
    ersist
    0.07
    tir
    0.07
    cake
    0.07
    antal
    0.07
    issance
    0.07
    -Based
    0.07
    ovÄĽ
    0.06
    aken
    0.06
    ivism
    0.06
    Activations Density 0.013%

    No Known Activations