© 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. 17-LLAMASCOPE-RES-131K
    11. 77118
    Prev
    Next
    INDEX
    Explanations

    references to cultural and artistic 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
    emit
    -0.08
    uchi
    -0.07
    erif
    -0.06
    emi
    -0.06
    vidence
    -0.06
    cellent
    -0.06
    ãģĦãĤĭ
    -0.06
     Klaus
    -0.06
    etÃŃ
    -0.06
    466
    -0.06
    POSITIVE LOGITS
    ura
    0.10
    wo
    0.08
    uras
    0.07
    urret
    0.07
    ÏĨÏħ
    0.07
    ãĥ¬ãĥ³
    0.07
    omb
    0.07
    @testable
    0.07
    ango
    0.06
    lease
    0.06
    Activations Density 0.006%

    No Known Activations