© 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. 62122
    Prev
    Next
    INDEX
    Explanations

    punctuation related to the flow of text

    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
    agos
    -0.07
    Responder
    -0.06
    eling
    -0.06
    istinguished
    -0.06
    AGO
    -0.06
    ovy
    -0.06
    dma
    -0.06
    agh
    -0.06
     mood
    -0.06
     Elli
    -0.06
    POSITIVE LOGITS
    cus
    0.07
    463
    0.07
    æĪª
    0.07
    çī
    0.07
    .syntax
    0.06
    omet
    0.06
    å¤
    0.06
    kil
    0.06
    vier
    0.06
    lycer
    0.06
    Activations Density 0.008%

    No Known Activations