© 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. 93281
    Prev
    Next
    INDEX
    Explanations

    references to judicial processes and capital punishment

    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
    Į
    -0.07
    ibri
    -0.07
    -mf
    -0.07
    andal
    -0.07
    917
    -0.07
    Prefs
    -0.06
    Instantiate
    -0.06
    .meta
    -0.06
    大å°ı
    -0.06
    á»ĭ
    -0.06
    POSITIVE LOGITS
    âĢ¦âĢ¦ãĢĤ
    0.07
     blocker
    0.06
     Death
    0.06
     death
    0.06
     OK
    0.06
    death
    0.06
    .rd
    0.06
    iet
    0.06
    eyi
    0.06
    JI
    0.05
    Activations Density 0.006%

    No Known Activations