© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83434
    Prev
    Next
    INDEX
    Explanations

    references to startups and innovative business practices

    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
     FAG
    -0.07
    ieux
    -0.07
    EventArgs
    -0.06
    career
    -0.06
    àµįà´
    -0.06
    iaux
    -0.06
    butt
    -0.06
    алов
    -0.06
    -contrib
    -0.06
    она
    -0.06
    POSITIVE LOGITS
    atri
    0.07
     Development
    0.07
    /demo
    0.07
    λÏİ
    0.07
     pitch
    0.07
     bootstrap
    0.07
     Pitch
    0.06
     traction
    0.06
     Pearson
    0.06
     development
    0.06
    Activations Density 0.029%

    No Known Activations