© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119674
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and contrasts

    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
    ERT
    -0.07
    igest
    -0.06
     treff
    -0.06
    yas
    -0.06
     stamp
    -0.06
    inet
    -0.06
     basics
    -0.06
     nejen
    -0.06
     besten
    -0.05
    ãģªãģĹ
    -0.05
    POSITIVE LOGITS
     previous
    0.09
     usual
    0.09
     typical
    0.08
    'autres
    0.08
     other
    0.08
     situation
    0.08
    previous
    0.08
    ekk
    0.07
     many
    0.07
     earlier
    0.07
    Activations Density 0.024%

    No Known Activations