© 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. 86732
    Prev
    Next
    INDEX
    Explanations

    references to historical Jewish figures involved in Zionist movements

    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
    Transparent
    -0.08
    arie
    -0.08
    Łèĥ½
    -0.07
    onden
    -0.07
    akis
    -0.07
     rencont
    -0.07
    áng
    -0.07
    ibold
    -0.07
    insic
    -0.07
    ief
    -0.07
    POSITIVE LOGITS
     early
    0.08
     late
    0.06
     anti
    0.06
     his
    0.06
     later
    0.06
     intellectually
    0.06
     prote
    0.06
     post
    0.06
     career
    0.06
     intellectual
    0.06
    Activations Density 0.018%

    No Known Activations