© 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. 74024
    Prev
    Next
    INDEX
    Explanations

    phrases related to youth programs and job training opportunities

    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
     university
    -0.06
    acific
    -0.06
    uzzer
    -0.06
    ipel
    -0.06
    acro
    -0.06
    ducation
    -0.06
     universities
    -0.06
    aben
    -0.06
    phinx
    -0.06
    ymous
    -0.06
    POSITIVE LOGITS
     Practical
    0.07
     Kiss
    0.07
     Minor
    0.07
     Spicer
    0.07
     bás
    0.06
     practical
    0.06
    림
    0.06
    _pwm
    0.06
    -kit
    0.06
    hotel
    0.06
    Activations Density 0.038%

    No Known Activations