© 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. 80418
    Prev
    Next
    INDEX
    Explanations

    instances of violence and suffering

    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
     hopefully
    -0.07
    pio
    -0.07
    igin
    -0.07
    anki
    -0.06
     mey
    -0.06
    ertas
    -0.06
    pios
    -0.06
    ieder
    -0.06
     Kend
    -0.06
    Forgery
    -0.06
    POSITIVE LOGITS
    ochen
    0.06
    avo
    0.06
    éľ
    0.06
    quer
    0.06
     prof
    0.06
     götür
    0.06
    .serializer
    0.06
     ê°Ģì§Ģ
    0.06
    .Void
    0.06
     جÙħع
    0.06
    Activations Density 0.012%

    No Known Activations