© 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 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. 40478
    Prev
    Next
    INDEX
    Explanations

    educational qualifications and career opportunities in various fields

    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
    ibur
    -0.06
    reff
    -0.06
    chine
    -0.06
    uta
    -0.06
     Lehr
    -0.06
    atorium
    -0.06
    aran
    -0.06
     shrink
    -0.05
     Persist
    -0.05
     profiler
    -0.05
    POSITIVE LOGITS
     graduates
    0.13
     graduate
    0.13
     graduating
    0.12
    educated
    0.12
     graduated
    0.12
    -educated
    0.12
     educated
    0.11
    grad
    0.11
     gradu
    0.11
     college
    0.10
    Activations Density 0.214%

    No Known Activations