© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104269
    Prev
    Next
    INDEX
    Explanations

    content related to password strength and security measures

    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
    éric
    -0.07
    morgan
    -0.07
    rawer
    -0.07
     FAG
    -0.06
     gad
    -0.06
    ανά
    -0.06
    éļĨ
    -0.06
     Moder
    -0.06
    ibal
    -0.06
    coc
    -0.06
    POSITIVE LOGITS
    å¼±
    0.07
    ulet
    0.06
    rompt
    0.06
    ullet
    0.06
    ency
    0.06
     Changing
    0.06
    issant
    0.06
    acente
    0.06
    azel
    0.06
     splash
    0.06
    Activations Density 0.007%

    No Known Activations