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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2539
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases that indicate relationships between ideas

    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
    ominator
    -0.06
    quee
    -0.06
    EM
    -0.06
    aload
    -0.06
     ing
    -0.06
     Bauer
    -0.06
    418
    -0.06
     Nichols
    -0.05
     attraction
    -0.05
    601
    -0.05
    POSITIVE LOGITS
    ÅĻÃŃz
    0.07
    enty
    0.07
    owie
    0.07
     ÙĪاÙĦتÙĬ
    0.07
    lifetime
    0.07
     âĹĦ
    0.06
     daÃŁ
    0.06
    .dtd
    0.06
    anel
    0.06
    -thumbnails
    0.06
    Activations Density 0.002%

    No Known Activations