© 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. 15-LLAMASCOPE-RES-131K
    11. 89531
    Prev
    Next
    INDEX
    Explanations

    personal development and learning experiences

    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
    reserve
    -0.07
    rored
    -0.06
     reserve
    -0.06
    oit
    -0.06
    ema
    -0.06
    oday
    -0.06
    lio
    -0.06
    mites
    -0.06
    shortcode
    -0.06
    alue
    -0.06
    POSITIVE LOGITS
    470
    0.07
     Pearson
    0.07
     further
    0.06
     formal
    0.06
    ^^
    0.06
    entai
    0.06
     Further
    0.06
    åŃĹå¹ķ
    0.06
    Further
    0.06
     termin
    0.06
    Activations Density 0.018%

    No Known Activations