© 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. 42556
    Prev
    Next
    INDEX
    Explanations

    references to design and branding in a business context

    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
    ifu
    -0.08
    enville
    -0.07
    äºĭ
    -0.07
     newcomer
    -0.07
    urr
    -0.06
    elta
    -0.06
    recipe
    -0.06
     newcomers
    -0.06
     Courtesy
    -0.06
    .defaults
    -0.06
    POSITIVE LOGITS
    zier
    0.07
     Scal
    0.07
     suggestion
    0.07
     please
    0.07
    ived
    0.07
     Yin
    0.07
    ektor
    0.06
     preferably
    0.06
     laure
    0.06
    hei
    0.06
    Activations Density 0.002%

    No Known Activations