© 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. 84341
    Prev
    Next
    INDEX
    Explanations

    references to union-related conflicts and struggles

    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
    icontrol
    -0.09
    jual
    -0.08
    ofi
    -0.08
    andler
    -0.08
    izr
    -0.08
    eya
    -0.08
    اÙĬات
    -0.07
    nemonic
    -0.07
    боÑĤ
    -0.07
    @protocol
    -0.07
    POSITIVE LOGITS
     union
    0.08
     invol
    0.07
    union
    0.06
     captive
    0.06
    chers
    0.06
     opting
    0.06
     pra
    0.06
    0.06
     workplace
    0.06
     Wisconsin
    0.06
    Activations Density 0.002%

    No Known Activations