© 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. 15-LLAMASCOPE-RES-131K
    11. 86845
    Prev
    Next
    INDEX
    Explanations

    references to humanitarian crises and the associated struggles of displaced individuals

    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
    allas
    -0.07
    amanho
    -0.07
    ť
    -0.07
    ubbo
    -0.06
    uty
    -0.06
     archive
    -0.06
     Vak
    -0.06
     أجÙĦ
    -0.06
    ubbles
    -0.06
    ĽĦ
    -0.06
    POSITIVE LOGITS
    erg
    0.07
     camp
    0.06
     camps
    0.06
    Animator
    0.06
    putc
    0.06
    ensi
    0.06
    ages
    0.06
     neu
    0.05
    atura
    0.05
    èĮĥ
    0.05
    Activations Density 0.008%

    No Known Activations