© 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. 41331
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts or confrontational situations

    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
    ستÙħ
    -0.08
    еко
    -0.08
    enstein
    -0.07
     tuto
    -0.07
    riter
    -0.07
    eza
    -0.07
    agh
    -0.07
    arna
    -0.07
    icz
    -0.07
    arget
    -0.07
    POSITIVE LOGITS
     their
    0.12
     its
    0.12
     him
    0.11
     his
    0.09
     them
    0.08
     itself
    0.08
     loro
    0.08
    their
    0.08
     lui
    0.08
     Its
    0.08
    Activations Density 0.105%

    No Known Activations