© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89738
    Prev
    Next
    INDEX
    Explanations

    references to social justice and activism

    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
    aris
    -0.08
    axter
    -0.07
    ึà¹Ī
    -0.07
     Ñĥп
    -0.07
    ughty
    -0.07
    ozo
    -0.07
    جة
    -0.07
    zzle
    -0.07
    DMI
    -0.07
    åĪĢ
    -0.07
    POSITIVE LOGITS
     demands
    0.07
     demanding
    0.07
     action
    0.06
     solidarity
    0.06
     underground
    0.06
     gal
    0.06
     Solid
    0.06
     Rosa
    0.06
     groups
    0.06
     civil
    0.06
    Activations Density 0.343%

    No Known Activations