© 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. 117504
    Prev
    Next
    INDEX
    Explanations

    concepts related to safety, security, and considerations when engaging with lotteries or similar activities

    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
    ertino
    -0.10
    jni
    -0.09
    formulario
    -0.09
    ï¼ĭ
    -0.09
    omap
    -0.09
    ãĢ
    -0.09
    бав
    -0.09
    (çģ«
    -0.09
    (æľ¨
    -0.09
     облиÑĩ
    -0.09
    POSITIVE LOGITS
     Bis
    0.06
    0.06
    s
    0.06
    atr
    0.06
    n
    0.06
    500
    0.05
     Wonder
    0.05
     Bans
    0.05
     Beh
    0.05
    o
    0.05
    Activations Density 0.003%

    No Known Activations