© 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 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. 88629
    Prev
    Next
    INDEX
    Explanations

    phrases related to causality and the effects of events

    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
    nett
    -0.07
    uga
    -0.07
    rez
    -0.07
     fod
    -0.07
     xong
    -0.07
    rint
    -0.07
    .kotlin
    -0.07
    odge
    -0.07
    bron
    -0.06
    γÏīν
    -0.06
    POSITIVE LOGITS
    /of
    0.06
    allah
    0.06
    /by
    0.06
    rys
    0.06
     due
    0.06
    æĸ¼
    0.06
     lack
    0.06
    -effects
    0.06
    /in
    0.06
     compr
    0.06
    Activations Density 0.022%

    No Known Activations