© 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. 129765
    Prev
    Next
    INDEX
    Explanations

    location and educational training related phrases

    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
    uben
    -0.07
    Pie
    -0.06
     Gian
    -0.06
    roz
    -0.06
    acerb
    -0.06
    ceptar
    -0.06
    Tube
    -0.06
    IEL
    -0.06
    sian
    -0.06
    amespace
    -0.06
    POSITIVE LOGITS
     Austin
    0.12
    Austin
    0.11
     Hyderabad
    0.10
     Texas
    0.10
     Tel
    0.10
    Texas
    0.10
    à°
    0.10
    amma
    0.09
     texas
    0.09
    à±
    0.09
    Activations Density 0.036%

    No Known Activations