© 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. 76632
    Prev
    Next
    INDEX
    Explanations

    terms related to security and cybersecurity

    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
    eya
    -0.08
    еÑĢб
    -0.07
    oser
    -0.07
    ãģĬãĤĬ
    -0.07
    ilter
    -0.07
    ALI
    -0.07
    ings
    -0.07
    ossible
    -0.07
    ncy
    -0.07
    jev
    -0.06
    POSITIVE LOGITS
    -minded
    0.09
     minded
    0.09
    .Cryptography
    0.08
    /security
    0.08
    tainment
    0.07
    -conscious
    0.07
    EZ
    0.07
    ÛĮÙĩ
    0.07
    jmu
    0.06
    CONDS
    0.06
    Activations Density 0.016%

    No Known Activations