© 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. 87572
    Prev
    Next
    INDEX
    Explanations

    terms related to online security and payment methods

    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
     Reeves
    -0.05
     Recovery
    -0.05
     FuÃŁ
    -0.05
     اش
    -0.05
    /fw
    -0.05
     free
    -0.05
     reklam
    -0.05
     Ko
    -0.05
     ho
    -0.05
     recovered
    -0.05
    POSITIVE LOGITS
     sécur
    0.09
    å®īåħ¨
    0.09
     secure
    0.08
     ìķĪìłĦ
    0.08
     Sec
    0.08
     Secure
    0.08
     SSL
    0.08
     sec
    0.08
     secured
    0.08
    Merchant
    0.08
    Activations Density 0.008%

    No Known Activations