© 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. 94687
    Prev
    Next
    INDEX
    Explanations

    mentions of various legal and societal issues related to poverty

    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
    ãĤīãģĹ
    -0.09
    INGLE
    -0.07
    ratings
    -0.07
    inge
    -0.06
    ingles
    -0.06
    arters
    -0.06
    ï¼ĺ
    -0.06
    iaux
    -0.06
    ãģĤãģĴ
    -0.06
    دÛĮگر
    -0.06
    POSITIVE LOGITS
    by
    0.07
     âĢİ
    0.06
    pillar
    0.06
    0.06
     Uncategorized
    0.06
    kud
    0.06
    -Clause
    0.06
     permalink
    0.05
    isset
    0.05
     ãĥ
    0.05
    Activations Density 0.047%

    No Known Activations