© 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. 59531
    Prev
    Next
    INDEX
    Explanations

    instances of serious legal charges and related incidents

    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
    umas
    -0.08
    å±Ģ
    -0.07
    eated
    -0.07
    Thin
    -0.07
    ELLOW
    -0.07
    RAIN
    -0.07
     byt
    -0.07
     Thin
    -0.06
    juan
    -0.06
    دÙĪد
    -0.06
    POSITIVE LOGITS
     crash
    0.10
     accident
    0.09
    ester
    0.07
     driver
    0.07
     driving
    0.07
    æĴ
    0.07
     pil
    0.07
     crashes
    0.06
     accidents
    0.06
     maximum
    0.06
    Activations Density 0.022%

    No Known Activations