© 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. 15507
    Prev
    Next
    INDEX
    Explanations

    references to malware and security-related information

    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
     interp
    -0.07
     bü
    -0.07
    STER
    -0.07
    icas
    -0.07
    @testable
    -0.07
     repr
    -0.07
    abet
    -0.07
    ipple
    -0.06
    eni
    -0.06
     imp
    -0.06
    POSITIVE LOGITS
    usercontent
    0.07
    ValueCollection
    0.06
    fusc
    0.06
    fuscated
    0.06
    .payload
    0.06
    walker
    0.06
    alom
    0.06
     targeting
    0.06
    .gstatic
    0.06
     targetType
    0.06
    Activations Density 0.013%

    No Known Activations