© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 105739
    Prev
    Next
    INDEX
    Explanations

    themes related to Jewish identity and its historical context, particularly in relation to violence and the Palestinian experience

    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
    ekler
    -0.07
    羣æŃ£
    -0.07
     true
    -0.06
    -real
    -0.06
    idas
    -0.06
     real
    -0.06
     buffer
    -0.06
    iesz
    -0.06
    วà¸ĩ
    -0.06
     Discrim
    -0.05
    POSITIVE LOGITS
     saja
    0.08
     negatives
    0.08
    gee
    0.08
     aspects
    0.08
     aspect
    0.08
    ngrx
    0.08
    negative
    0.07
     negative
    0.07
    *[
    0.07
    aspect
    0.07
    Activations Density 0.034%

    No Known Activations