© 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. 62111
    Prev
    Next
    INDEX
    Explanations

    references to violent incidents and their implications

    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
    loo
    -0.07
    ça
    -0.06
    ãĥĹãĥª
    -0.06
    modele
    -0.06
     mistr
    -0.06
    дина
    -0.06
     Leban
    -0.06
    ksi
    -0.06
    âĢ¦.↵↵
    -0.06
    íıŃ
    -0.06
    POSITIVE LOGITS
     happening
    0.13
     occurring
    0.13
     involving
    0.12
     occurred
    0.11
     happened
    0.10
     ocur
    0.10
     xảy
    0.10
     happen
    0.10
    åıijçĶŁ
    0.10
     occur
    0.10
    Activations Density 0.070%

    No Known Activations