© 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. 81578
    Prev
    Next
    INDEX
    Explanations

    phrases related to children's literacy and educational programs

    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
    locker
    -0.08
    _STAGE
    -0.07
    _fetch
    -0.06
    enger
    -0.06
     fetch
    -0.06
    estate
    -0.06
    ạch
    -0.06
    .dylib
    -0.06
    ija
    -0.06
     servisi
    -0.06
    POSITIVE LOGITS
     basic
    0.07
     dignity
    0.06
     Starter
    0.06
    orra
    0.06
    _UNIX
    0.06
     basics
    0.06
    ONENT
    0.06
    imus
    0.06
    iazza
    0.06
    ĥ
    0.06
    Activations Density 0.017%

    No Known Activations