© 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. 39091
    Prev
    Next
    INDEX
    Explanations

    events related to military or violent actions

    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
    á»iji
    -0.08
    arges
    -0.08
    ãĥ³ãĥĢ
    -0.07
    RTC
    -0.07
    238
    -0.06
    agnost
    -0.06
    ÑĸÑĶ
    -0.06
    istrovstvÃŃ
    -0.06
    559
    -0.06
    anos
    -0.06
    POSITIVE LOGITS
     claiming
    0.08
     claim
    0.07
     GDK
    0.06
     claimed
    0.06
    engu
    0.06
    quer
    0.06
     claims
    0.06
    asco
    0.06
    _prepare
    0.06
    alon
    0.06
    Activations Density 0.014%

    No Known Activations