© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 107856
    Prev
    Next
    INDEX
    Explanations

    names of geographic locations, particularly those of universities or regions in the United States

    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
    izzo
    -0.08
    MLElement
    -0.07
    ÄįÃŃ
    -0.07
    ึà¸ģ
    -0.07
    ÄĽÅ¾
    -0.07
    mlin
    -0.07
    innie
    -0.07
    lemen
    -0.07
     æº
    -0.06
    arlar
    -0.06
    POSITIVE LOGITS
    erton
    0.06
    DU
    0.06
    borough
    0.06
    omi
    0.06
    .edu
    0.06
    à¹ģห
    0.06
    ChangedEventArgs
    0.05
     Sciences
    0.05
    ophil
    0.05
    -scalable
    0.05
    Activations Density 0.007%

    No Known Activations