© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96921
    Prev
    Next
    INDEX
    Explanations

    references to anti-Semitic sentiments or expressions

    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
    arrera
    -0.07
    uli
    -0.07
    ddy
    -0.07
    leon
    -0.06
    ji
    -0.06
    åħ»
    -0.06
    uur
    -0.06
     Doch
    -0.06
    .removeAttribute
    -0.06
    ARRIER
    -0.06
    POSITIVE LOGITS
    /in
    0.07
     Erl
    0.06
     Ler
    0.06
    OLT
    0.06
    ishly
    0.06
    (er
    0.06
     Er
    0.06
    /id
    0.05
    BM
    0.05
     Bert
    0.05
    Activations Density 0.011%

    No Known Activations