© 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. 15-LLAMASCOPE-RES-131K
    11. 86378
    Prev
    Next
    INDEX
    Explanations

    legal terms and classifications related to serious crimes

    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
     Justice
    -0.06
    Justice
    -0.05
    ersen
    -0.05
     moz
    -0.05
    ieg
    -0.05
    poÄįet
    -0.05
    éij
    -0.05
    .githubusercontent
    -0.05
     whole
    -0.05
    /me
    -0.05
    POSITIVE LOGITS
    amt
    0.07
     Heap
    0.07
     зан
    0.07
    ãĥ¼ãĥį
    0.07
    OLA
    0.07
    yas
    0.07
    ickers
    0.07
    icot
    0.07
     cấp
    0.07
    çĤİ
    0.07
    Activations Density 0.005%

    No Known Activations