© 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. 17424
    Prev
    Next
    INDEX
    Explanations

    references to academic programs and institutions in social work

    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
    urgeon
    -0.09
    uggy
    -0.07
    ssel
    -0.07
    Ñģен
    -0.07
    å°ĸ
    -0.07
    оÑĢод
    -0.07
    zos
    -0.07
     nackte
    -0.07
    ustr
    -0.07
    ائÙĬ
    -0.07
    POSITIVE LOGITS
     agency
    0.08
     social
    0.08
     client
    0.07
     agencies
    0.07
     Social
    0.07
     clients
    0.07
     cas
    0.07
    -client
    0.07
     Bowl
    0.07
    social
    0.06
    Activations Density 0.024%

    No Known Activations