© 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. 18100
    Prev
    Next
    INDEX
    Explanations

    geographic locations and island names

    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
    uset
    -0.06
    ümÃ¼ÅŁ
    -0.06
    ury
    -0.06
     era
    -0.06
    emed
    -0.06
    951
    -0.06
    ãĥªãĤ«
    -0.06
    èħIJ
    -0.06
    omo
    -0.06
    ecta
    -0.06
    POSITIVE LOGITS
     Island
    0.16
     island
    0.16
    島
    0.15
    å²Ľ
    0.13
     islands
    0.10
     Islands
    0.10
     оÑģÑĤÑĢов
    0.10
     Islanders
    0.09
    ense
    0.07
    ensis
    0.07
    Activations Density 0.037%

    No Known Activations