© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14356
    Prev
    Next
    INDEX
    Explanations

    information about locations and durations related to events or entities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ron
    -0.07
    rol
    -0.06
    mate
    -0.06
     reality
    -0.05
     (++
    -0.05
    pron
    -0.05
    акÑģим
    -0.05
    468
    -0.05
    inx
    -0.05
     fort
    -0.05
    POSITIVE LOGITS
     original
    0.09
    -original
    0.09
     location
    0.09
     locations
    0.09
    åİŁ
    0.09
     ORIGINAL
    0.08
    original
    0.08
     åİŁ
    0.08
     unchanged
    0.08
     current
    0.08
    Activations Density 0.061%

    No Known Activations