© 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. 106255
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical entities and their relationships

    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
    enna
    -0.07
    amburger
    -0.07
    ISOString
    -0.07
    arah
    -0.07
    å¥ij
    -0.07
    .MSG
    -0.07
     ley
    -0.07
    enn
    -0.07
    ToLocal
    -0.06
    bard
    -0.06
    POSITIVE LOGITS
     interven
    0.06
    .yang
    0.06
     intervention
    0.06
     Maul
    0.06
     neob
    0.06
    -led
    0.06
    .closest
    0.06
    748
    0.06
     synth
    0.06
     spoilers
    0.06
    Activations Density 0.061%

    No Known Activations