© 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. 4289
    Prev
    Next
    INDEX
    Explanations

    themes related to social justice and the treatment of marginalized individuals

    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
    uess
    -0.07
    omor
    -0.07
    aign
    -0.07
    evt
    -0.07
    unde
    -0.07
     Clerk
    -0.07
     #__
    -0.07
    еÑĢк
    -0.07
    izza
    -0.06
    .pkg
    -0.06
    POSITIVE LOGITS
    elsea
    0.07
     Mid
    0.06
    verages
    0.06
    oled
    0.06
    -valu
    0.06
    ivot
    0.06
     Wizards
    0.06
    ertools
    0.06
     Ac
    0.06
     Mits
    0.06
    Activations Density 0.005%

    No Known Activations