© 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. 15898
    Prev
    Next
    INDEX
    Explanations

    elements related to violence or confrontation

    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
     kraje
    -0.07
    props
    -0.07
    984
    -0.06
    SetBranch
    -0.06
    orate
    -0.06
    odel
    -0.05
    Log
    -0.05
    adian
    -0.05
    amma
    -0.05
    754
    -0.05
    POSITIVE LOGITS
    è¢ĭ
    0.08
    aryl
    0.07
    usp
    0.07
    æĢĢ
    0.07
    umbing
    0.06
     ê
    0.06
     pocket
    0.06
    indr
    0.06
    ÑĢÑİ
    0.06
    jours
    0.06
    Activations Density 0.013%

    No Known Activations