© 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. 89076
    Prev
    Next
    INDEX
    Explanations

    entities related to crime and legal issues

    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
    otti
    -0.08
     Fal
    -0.07
    ajar
    -0.07
     nargin
    -0.06
    ìĹŃ
    -0.06
    fff
    -0.06
    ioc
    -0.06
     QDir
    -0.06
    fx
    -0.06
    æµİ
    -0.06
    POSITIVE LOGITS
     allegedly
    0.06
     mism
    0.06
    åħĪçĶŁ
    0.06
    isko
    0.06
    hest
    0.06
    makta
    0.06
    jours
    0.06
    ltk
    0.06
    agg
    0.06
    -pane
    0.06
    Activations Density 0.013%

    No Known Activations