© 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. 15-LLAMASCOPE-RES-131K
    11. 87417
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity attacks and vulnerabilities

    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
    -Sah
    -0.07
    owski
    -0.07
    ects
    -0.07
    eprom
    -0.07
    uchar
    -0.07
    .fi
    -0.06
    yles
    -0.06
    oppins
    -0.06
    ThreadId
    -0.06
    apı
    -0.06
    POSITIVE LOGITS
     attack
    0.08
     McA
    0.07
     attacks
    0.07
    unga
    0.07
     Target
    0.07
     vind
    0.06
    ź
    0.06
    idan
    0.06
    kova
    0.06
     Attack
    0.06
    Activations Density 0.010%

    No Known Activations