© 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. 15-LLAMASCOPE-RES-131K
    11. 26683
    Prev
    Next
    INDEX
    Explanations

    words associated with significant personalities and well-known cultural references

    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
    rat
    -0.07
    ooke
    -0.07
    Ùħار
    -0.07
    erner
    -0.07
    listener
    -0.07
    ovo
    -0.06
    raci
    -0.06
    ople
    -0.06
    ãĥªãĥ¼
    -0.06
    esse
    -0.06
    POSITIVE LOGITS
    UNC
    0.07
    idian
    0.06
    atrix
    0.06
     plá
    0.06
     Range
    0.06
    ören
    0.06
    OutOfRangeException
    0.06
     lẽ
    0.06
    orest
    0.06
    گاÙĨÛĮ
    0.06
    Activations Density 0.001%

    No Known Activations