© 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. 57364
    Prev
    Next
    INDEX
    Explanations

    references to security and personal information in online lottery contexts

    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
     Ot
    -0.07
    ao
    -0.07
    Ot
    -0.06
     Otto
    -0.06
     dating
    -0.06
     Forg
    -0.06
    ouden
    -0.06
    fix
    -0.06
    anga
    -0.06
    onen
    -0.06
    POSITIVE LOGITS
     withdrawal
    0.10
     Withdraw
    0.08
     Wire
    0.08
     withdrawing
    0.08
    withdraw
    0.08
     withdrawals
    0.08
     withdraw
    0.07
     transfers
    0.07
     withdrew
    0.07
     wire
    0.07
    Activations Density 0.010%

    No Known Activations