© 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. 107539
    Prev
    Next
    INDEX
    Explanations

    references to humanitarian aid and communal gatherings in crisis situations

    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
    adle
    -0.06
    avern
    -0.06
     env
    -0.06
    .eval
    -0.06
    onga
    -0.05
     Mile
    -0.05
    DMA
    -0.05
     torch
    -0.05
    oze
    -0.05
    asu
    -0.05
    POSITIVE LOGITS
     unarmed
    0.08
    oley
    0.07
    upport
    0.07
    _prot
    0.07
    αÏģά
    0.07
    -navbar
    0.06
    overlap
    0.06
    nung
    0.06
    ÙĨداÙĨ
    0.06
    innen
    0.06
    Activations Density 0.001%

    No Known Activations