© 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 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. 126540
    Prev
    Next
    INDEX
    Explanations

    locations or concepts associated with gatherings, shelters, and hubs

    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
    acha
    -0.09
    gili
    -0.09
    burger
    -0.09
    Ïģκ
    -0.08
    itler
    -0.08
    омен
    -0.08
    -valu
    -0.08
    veis
    -0.08
    (æľĪ
    -0.08
    berger
    -0.08
    POSITIVE LOGITS
     for
    0.14
     where
    0.11
    for
    0.09
     bagi
    0.08
     длÑı
    0.08
     für
    0.08
     för
    0.08
     of
    0.07
     voor
    0.07
    0.07
    Activations Density 0.024%

    No Known Activations