© 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. 126568
    Prev
    Next
    INDEX
    Explanations

    references to societal issues related to violence and the justice system

    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
     now
    -0.07
    ager
    -0.06
     daily
    -0.06
     Currently
    -0.06
     currently
    -0.06
    ais
    -0.06
     nightly
    -0.06
    ih
    -0.06
     hala
    -0.06
    currently
    -0.06
    POSITIVE LOGITS
     usually
    0.18
     often
    0.18
     sometimes
    0.16
    often
    0.15
    usually
    0.15
     Often
    0.14
    Often
    0.14
    ometimes
    0.13
     Usually
    0.13
    sometimes
    0.13
    Activations Density 0.011%

    No Known Activations