© 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. 17-LLAMASCOPE-RES-131K
    11. 92350
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic depictions of urban landscapes and social issues

    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
    antino
    -0.08
    åĿĬ
    -0.08
    sten
    -0.07
    oples
    -0.07
    elow
    -0.07
    Subsystem
    -0.07
     metav
    -0.07
    atron
    -0.07
    .newBuilder
    -0.07
    éĤ¦
    -0.06
    POSITIVE LOGITS
    utor
    0.06
     Thi
    0.06
    ÅĻe
    0.06
    让æĪij
    0.06
    лим
    0.06
    کر
    0.05
     c
    0.05
    ENDOR
    0.05
     specific
    0.05
    uran
    0.05
    Activations Density 0.054%

    No Known Activations