© 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 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. 29457
    Prev
    Next
    INDEX
    Explanations

    terms related to the ongoing conflict and occupation affecting the Palestinian population

    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
    èĪĴ
    -0.06
    rim
    -0.06
    驾
    -0.06
    alam
    -0.06
    ius
    -0.06
    idine
    -0.06
    izzer
    -0.05
     mixed
    -0.05
    çı
    -0.05
    irm
    -0.05
    POSITIVE LOGITS
    ÑĥÑĤÑĮ
    0.08
    .shtml
    0.08
    URLException
    0.07
    icut
    0.07
    ëį°ìĿ´íĬ¸
    0.07
    omanip
    0.07
     dirty
    0.07
     Dirty
    0.06
    anten
    0.06
    cki
    0.06
    Activations Density 0.001%

    No Known Activations