© 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. 108595
    Prev
    Next
    INDEX
    Explanations

    references to RV designs and specifications

    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
    idot
    -0.08
    inou
    -0.08
    vio
    -0.07
    åijĬ
    -0.07
     sami
    -0.07
    å·»
    -0.07
     Helm
    -0.07
    lags
    -0.06
     readiness
    -0.06
    bos
    -0.06
    POSITIVE LOGITS
     design
    0.09
     proportions
    0.08
     Design
    0.07
     plan
    0.07
    åłĤ
    0.06
    Design
    0.06
     cheap
    0.06
    设计
    0.06
     Inspired
    0.06
     Ideas
    0.06
    Activations Density 0.031%

    No Known Activations