© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 108964
    Prev
    Next
    INDEX
    Explanations

    Java utility classes and their related components

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    133
    -0.08
    lessly
    -0.07
    оже
    -0.07
    Ñģлов
    -0.07
    edException
    -0.06
    Fab
    -0.06
    OKEN
    -0.06
    ont
    -0.06
    elles
    -0.06
    arp
    -0.06
    POSITIVE LOGITS
    .concurrent
    0.08
    .ArrayList
    0.07
    .logging
    0.07
    .Collections
    0.06
    .List
    0.06
    .Arrays
    0.06
    anean
    0.06
    .spi
    0.06
    å¿Ĩ
    0.06
    olist
    0.06
    Activations Density 0.001%

    No Known Activations