© 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. 17-LLAMASCOPE-RES-131K
    11. 2878
    Prev
    Next
    INDEX
    Explanations

    phrases indicating internal conflicts or struggles

    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
    алÑİ
    -0.09
    ALER
    -0.09
    qus
    -0.08
    .MixedReality
    -0.08
    edm
    -0.08
     Foley
    -0.08
    imson
    -0.07
    nde
    -0.07
    ALAR
    -0.07
    bai
    -0.07
    POSITIVE LOGITS
     self
    0.10
     himself
    0.07
     themselves
    0.06
     author
    0.06
     Self
    0.06
     owner
    0.06
    elf
    0.06
     according
    0.06
    -self
    0.06
     participants
    0.06
    Activations Density 0.095%

    No Known Activations