© 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. 73391
    Prev
    Next
    INDEX
    Explanations

    references to legal and financial misconduct

    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
    alars
    -0.08
    .scalablytyped
    -0.08
     lawy
    -0.07
    assi
    -0.07
    loquent
    -0.07
    ebo
    -0.07
    mans
    -0.07
    olesterol
    -0.07
     IMM
    -0.07
    stal
    -0.07
    POSITIVE LOGITS
     repeatedly
    0.07
     numerous
    0.06
    askell
    0.06
    il
    0.06
     Center
    0.06
     falsely
    0.06
     nonexistent
    0.06
     various
    0.06
     several
    0.06
    663
    0.05
    Activations Density 0.018%

    No Known Activations