© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28426
    Prev
    Next
    INDEX
    Explanations

    terms related to student loan assistance and debt relief

    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
     Bones
    -0.08
    imson
    -0.07
     extradition
    -0.07
    .scalablytyped
    -0.07
    PÅĻi
    -0.07
    è¨Ĥ
    -0.07
    Ìĥ
    -0.06
    .Callback
    -0.06
     Kam
    -0.06
    pek
    -0.06
    POSITIVE LOGITS
    rav
    0.06
     Elig
    0.06
     housing
    0.06
    æĪ¸
    0.06
     conserv
    0.06
     eligibility
    0.06
    struct
    0.06
    ":[{↵
    0.06
     households
    0.06
    zsche
    0.06
    Activations Density 0.003%

    No Known Activations