© 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. 125764
    Prev
    Next
    INDEX
    Explanations

    references to disputes or conflicts involving government and mining operations

    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
    itesse
    -0.07
    annon
    -0.07
    ayet
    -0.07
    gas
    -0.06
     Antar
    -0.06
    odo
    -0.06
    iglia
    -0.06
    aber
    -0.06
    ikal
    -0.06
    aston
    -0.06
    POSITIVE LOGITS
     mining
    0.12
     mine
    0.11
     Mining
    0.11
     miners
    0.10
     gold
    0.10
    Mining
    0.10
     Mine
    0.09
     mines
    0.09
    Mine
    0.08
     ore
    0.08
    Activations Density 0.113%

    No Known Activations