© 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. 17-LLAMASCOPE-RES-131K
    11. 16019
    Prev
    Next
    INDEX
    Explanations

    references to significant negative events or conditions

    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
    ensch
    -0.06
    æĮ¯ãĤĬ
    -0.06
    ankind
    -0.06
    ationToken
    -0.06
    chas
    -0.05
    oks
    -0.05
    woff
    -0.05
    ViewById
    -0.05
    ANK
    -0.05
     Orn
    -0.05
    POSITIVE LOGITS
    201
    0.10
    199
    0.09
    200
    0.08
    198
    0.07
    asal
    0.07
     earlier
    0.07
    myp
    0.06
    umblr
    0.06
     offsetof
    0.06
    jo
    0.06
    Activations Density 0.018%

    No Known Activations