© 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. 17-LLAMASCOPE-RES-131K
    11. 129325
    Prev
    Next
    INDEX
    Explanations

    references to societal behaviors and political scenarios

    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
    raq
    -0.07
    iyorum
    -0.07
    istrat
    -0.07
    avor
    -0.07
    είÏĦε
    -0.07
    èģĶç½ij
    -0.07
     sona
    -0.07
     mÃł
    -0.07
    phinx
    -0.07
    .grp
    -0.07
    POSITIVE LOGITS
     would
    0.37
    would
    0.32
     Would
    0.30
    Would
    0.28
     wouldn
    0.24
     skulle
    0.22
     zou
    0.21
     würde
    0.20
     serait
    0.20
     бÑĭ
    0.18
    Activations Density 0.259%

    No Known Activations