© 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. 125242
    Prev
    Next
    INDEX
    Explanations

    references to code structure and data manipulation in programming

    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
    mÃŃ
    -0.08
    ared
    -0.07
    Ïĩα
    -0.07
    ichel
    -0.06
    ifies
    -0.06
    ãİ
    -0.06
    éŃĶæ³ķ
    -0.06
    zz
    -0.06
    опол
    -0.06
    説
    -0.06
    POSITIVE LOGITS
    ynamo
    0.07
     certain
    0.07
    alim
    0.07
     my
    0.07
     another
    0.06
    æĪijçļĦ
    0.06
    .my
    0.06
    _qos
    0.06
     опÑĢеделен
    0.06
    .persist
    0.06
    Activations Density 0.018%

    No Known Activations