© 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 EvalsExportsinterp-engineNEWAPI 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. 95588
    Prev
    Next
    INDEX
    Explanations

    references to authors and their works, particularly in the context of LGBTQ literature

    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
    elia
    -0.07
    pecia
    -0.07
    eyse
    -0.07
    ectors
    -0.07
    AGMA
    -0.07
    eydi
    -0.06
    NV
    -0.06
     Zaman
    -0.06
    erp
    -0.06
    endale
    -0.06
    POSITIVE LOGITS
    енÑģ
    0.07
     Benchmark
    0.07
    νÏī
    0.06
     Anthrop
    0.06
    GIN
    0.06
    udios
    0.06
    .jd
    0.06
    taÅŁ
    0.06
    å®ĺç½ij
    0.06
    aru
    0.06
    Activations Density 0.011%

    No Known Activations