© 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. 82825
    Prev
    Next
    INDEX
    Explanations

    technical vulnerabilities and security issues related to data encryption and authentication

    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
    pector
    -0.08
     autorelease
    -0.08
    _EXTERN
    -0.07
    ãĥ¼ãĥĨãĤ£
    -0.07
     Hubb
    -0.07
    -svg
    -0.07
    üy
    -0.07
    olit
    -0.07
     Heritage
    -0.07
    _fixture
    -0.06
    POSITIVE LOGITS
     security
    0.08
    security
    0.07
     safety
    0.07
     protection
    0.07
    -security
    0.06
     theft
    0.06
     trusting
    0.06
     ob
    0.06
     server
    0.06
    keh
    0.06
    Activations Density 0.013%

    No Known Activations