© 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. 54137
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to the Holocaust and its historical context

    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
     Lon
    -0.07
     mast
    -0.07
    rip
    -0.07
    eph
    -0.07
    acro
    -0.06
     Dia
    -0.06
     Fon
    -0.06
    ahl
    -0.06
    vas
    -0.06
    xes
    -0.06
    POSITIVE LOGITS
     Auschwitz
    0.13
     Holocaust
    0.12
     Jews
    0.10
     Jewish
    0.10
     concentration
    0.09
     Nazi
    0.09
    194
    0.09
     Jew
    0.08
    ocaust
    0.08
     jewish
    0.08
    Activations Density 0.163%

    No Known Activations