© 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. 5428
    Prev
    Next
    INDEX
    Explanations

    references to inmates and related experiences in prison settings

    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
    contri
    -0.06
    AGMA
    -0.06
    avern
    -0.06
    Ø´ÙĪر
    -0.06
    dration
    -0.06
    UF
    -0.06
     Siri
    -0.06
     convent
    -0.06
    ikut
    -0.06
    ÚĺÙĩ
    -0.06
    POSITIVE LOGITS
     prisoners
    0.08
     inside
    0.08
     prison
    0.08
     Inside
    0.08
     prisoner
    0.08
     inmates
    0.08
    inside
    0.07
     parole
    0.07
     Prison
    0.07
     inmate
    0.07
    Activations Density 0.006%

    No Known Activations