© 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. 2645
    Prev
    Next
    INDEX
    Explanations

    discussions about the implications and consequences of student debt

    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
    ernet
    -0.07
    imas
    -0.07
    orer
    -0.07
     grade
    -0.06
    cod
    -0.06
    lander
    -0.06
    loor
    -0.06
     Grade
    -0.06
    uw
    -0.06
    uro
    -0.06
    POSITIVE LOGITS
    529
    0.09
     financing
    0.07
     Financing
    0.07
    tu
    0.07
     Entrance
    0.07
     entrance
    0.07
    uition
    0.07
     Stack
    0.07
     financial
    0.06
     tu
    0.06
    Activations Density 0.022%

    No Known Activations