© 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. 117786
    Prev
    Next
    INDEX
    Explanations

    content related to early childhood learning and parental involvement in education

    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
    .scalablytyped
    -0.07
    rez
    -0.07
    ono
    -0.07
     eth
    -0.07
    jÃŃt
    -0.06
    arel
    -0.06
    rung
    -0.06
     Anonymous
    -0.06
    cura
    -0.06
    emento
    -0.06
    POSITIVE LOGITS
    abra
    0.07
    odule
    0.07
    363
    0.07
    iture
    0.07
     homeschool
    0.07
     Reading
    0.06
     Yesterday
    0.06
     yesterday
    0.06
    BitConverter
    0.06
    Ïģή
    0.06
    Activations Density 0.003%

    No Known Activations