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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71582
    Prev
    Next
    INDEX
    Explanations

    expressions related to social and political tensions regarding Jewish identity and history

    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
    mma
    -0.07
     Dipl
    -0.07
    apiro
    -0.06
     Gee
    -0.06
    ág
    -0.06
    ervisor
    -0.06
     Plan
    -0.06
    uitka
    -0.06
    andex
    -0.06
    uong
    -0.06
    POSITIVE LOGITS
     Witness
    0.07
    reau
    0.06
    ấm
    0.06
     generation
    0.06
    REATED
    0.06
    -generation
    0.06
    士
    0.06
    bakan
    0.06
    ÅŁa
    0.06
     lidi
    0.06
    Activations Density 0.012%

    No Known Activations