© 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. 86622
    Prev
    Next
    INDEX
    Explanations

    references to cybersecurity and hacking incidents related to user accounts

    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
     Mend
    -0.08
    svp
    -0.07
    zf
    -0.06
    lash
    -0.06
     Bauer
    -0.06
    æķ¬
    -0.06
    agenta
    -0.06
    æı
    -0.06
    liable
    -0.06
    /address
    -0.06
    POSITIVE LOGITS
     account
    0.09
    hani
    0.07
    coni
    0.07
     settings
    0.07
     sess
    0.06
     ØŃساب
    0.06
     Account
    0.06
     recovery
    0.06
    erra
    0.06
    rimon
    0.06
    Activations Density 0.005%

    No Known Activations