© 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. 27251
    Prev
    Next
    INDEX
    Explanations

    terms related to support for various groups in need, including families, children, and those experiencing hardships

    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
    okt
    -0.07
    ãĤ¦ãĥ³
    -0.07
    etch
    -0.06
    orest
    -0.06
     Nelson
    -0.06
    iox
    -0.06
    ield
    -0.06
    ActionTypes
    -0.06
    ame
    -0.06
    hare
    -0.06
    POSITIVE LOGITS
    å¿Ļ
    0.09
     understand
    0.08
    reh
    0.07
     Äijỡ
    0.07
     become
    0.06
    oru
    0.06
    obus
    0.06
    unsubscribe
    0.06
    itom
    0.06
    .epam
    0.06
    Activations Density 0.044%

    No Known Activations