© 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. 59504
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical entities and issues related to conflicts

    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
    polator
    -0.08
    imers
    -0.07
    ired
    -0.07
    ÑĥÑĤÑĮ
    -0.07
     ydk
    -0.07
    IRQ
    -0.07
    âĢ¦.↵↵
    -0.06
    ORIA
    -0.06
     uv
    -0.06
    ÄįnÃŃ
    -0.06
    POSITIVE LOGITS
    -vs
    0.07
    -vers
    0.07
     vs
    0.07
     versus
    0.07
     Vs
    0.06
     cent
    0.06
    acter
    0.06
     turn
    0.06
     drive
    0.06
     phase
    0.06
    Activations Density 0.060%

    No Known Activations