© 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. 103171
    Prev
    Next
    INDEX
    Explanations

    instances of serious legal issues or criminal 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
    ãĥĹãĥª
    -0.08
     #__
    -0.08
    pard
    -0.08
     TMPro
    -0.07
    ourg
    -0.07
    ãĥ¼ãĥķ
    -0.07
    .Debugger
    -0.07
    ôme
    -0.07
    ÄIJT
    -0.07
     fich
    -0.07
    POSITIVE LOGITS
    0.06
     Penny
    0.06
     Hod
    0.06
     racially
    0.06
    etal
    0.05
     another
    0.05
     Gim
    0.05
    erek
    0.05
     house
    0.05
     dogs
    0.05
    Activations Density 0.037%

    No Known Activations