© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77094
    Prev
    Next
    INDEX
    Explanations

    terms related to Jewish identity and contemporary political discussions surrounding Israel and Palestine

    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
    sic
    -0.07
    ALER
    -0.06
    dge
    -0.06
    ichel
    -0.06
    edic
    -0.06
    RU
    -0.06
    ITT
    -0.06
    itt
    -0.06
    ioneer
    -0.06
    rijk
    -0.06
    POSITIVE LOGITS
     particular
    0.09
     whether
    0.09
    ossier
    0.08
    æĺ¯åIJ¦
    0.08
     WHETHER
    0.08
     ultimately
    0.08
     individual
    0.08
     æĺ¯åIJ¦
    0.08
     specific
    0.07
    whether
    0.07
    Activations Density 0.037%

    No Known Activations