© 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. 29350
    Prev
    Next
    INDEX
    Explanations

    terms related to restorative justice and healing

    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
    ¦
    -0.07
    æŁı
    -0.06
     Sez
    -0.06
    mez
    -0.06
     adm
    -0.06
    ouro
    -0.06
     cav
    -0.06
     kov
    -0.06
    ODE
    -0.06
    POSE
    -0.06
    POSITIVE LOGITS
     justice
    0.07
    ubuntu
    0.07
    zÄħ
    0.07
     Victim
    0.07
     heals
    0.07
     tang
    0.07
     victim
    0.07
    oled
    0.07
     Gand
    0.06
    íĮ¨
    0.06
    Activations Density 0.001%

    No Known Activations