© 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. 63060
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and humanitarian efforts

    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
     Bilg
    -0.07
    Spain
    -0.07
     Pow
    -0.06
     Spain
    -0.06
     sy
    -0.06
    _irq
    -0.06
    leep
    -0.06
     Daw
    -0.06
     Nigerian
    -0.06
     Nigeria
    -0.06
    POSITIVE LOGITS
     Hond
    0.10
     ника
    0.09
     Nicar
    0.09
     Honduras
    0.09
     Costa
    0.08
     Central
    0.07
     Nicaragua
    0.07
     Panama
    0.07
     Liberia
    0.07
     Exodus
    0.07
    Activations Density 0.052%

    No Known Activations