© 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 EvalsExportsinterp-engineNEWAPI 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. 94697
    Prev
    Next
    INDEX
    Explanations

    terms related to legal charges and convictions

    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
    odka
    -0.07
    çuk
    -0.06
    iele
    -0.06
    reur
    -0.06
    ÙĦÙĬÙĩ
    -0.06
    ëĭĿ
    -0.06
    ibil
    -0.06
    liable
    -0.06
    aison
    -0.06
    imoto
    -0.06
    POSITIVE LOGITS
     crime
    0.08
    elry
    0.07
     crimes
    0.07
    esa
    0.07
    uzzi
    0.06
    668
    0.06
     forfe
    0.06
     criminal
    0.06
     Trustees
    0.06
    éIJ
    0.06
    Activations Density 0.014%

    No Known Activations