© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 74730
    Prev
    Next
    INDEX
    Explanations

    terms related to territorial occupation and its associated conflicts

    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
     impro
    -0.06
     native
    -0.06
    777
    -0.06
     Allied
    -0.06
    RAIN
    -0.05
     Organisation
    -0.05
    302
    -0.05
     tick
    -0.05
    plits
    -0.05
     Ark
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.08
    alytics
    0.08
    hoff
    0.08
    #echo
    0.07
    olib
    0.07
    iyon
    0.07
    aturday
    0.07
    ioni
    0.07
     ÑģÑĥÑĤ
    0.07
    utin
    0.07
    Activations Density 0.001%

    No Known Activations