© 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. 106246
    Prev
    Next
    INDEX
    Explanations

    geographical or historical place names related to the region of Israel and surrounding areas

    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
    ural
    -0.06
     warrant
    -0.06
    ofi
    -0.06
    unks
    -0.05
     Abb
    -0.05
    etypes
    -0.05
    nor
    -0.05
     od
    -0.05
    asi
    -0.05
     ni
    -0.05
    POSITIVE LOGITS
    ÑģÑĮого
    0.09
    erland
    0.07
    à¥įà¤Ĺत
    0.07
    çĸ«
    0.07
    esium
    0.07
    ãģĹãĤĥ
    0.07
    جز
    0.07
     Ä°li
    0.07
     Mons
    0.07
    enÄĽ
    0.07
    Activations Density 0.071%

    No Known Activations