© 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. 124514
    Prev
    Next
    INDEX
    Explanations

    information related to system vulnerabilities and attacks

    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
    окÑĢема
    -0.07
    ίλ
    -0.07
     hatta
    -0.07
    stal
    -0.07
    ÎijÎł
    -0.06
     arcs
    -0.06
    aka
    -0.06
    ÑĢаÑĤно
    -0.06
     NT
    -0.06
    Ư
    -0.06
    POSITIVE LOGITS
     Although
    0.07
     Despite
    0.07
     aside
    0.07
     Aside
    0.07
     While
    0.07
     Besides
    0.07
     There
    0.07
     nothing
    0.07
     Because
    0.07
    There
    0.07
    Activations Density 0.027%

    No Known Activations