© 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. 129768
    Prev
    Next
    INDEX
    Explanations

    historical figures and their relevant information

    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
    astle
    -0.07
    prech
    -0.07
    habi
    -0.07
    èo
    -0.07
    prm
    -0.07
    rende
    -0.07
    cheon
    -0.07
    aset
    -0.07
    asury
    -0.07
    xmm
    -0.07
    POSITIVE LOGITS
    193
    0.09
    RTC
    0.06
    192
    0.06
    ering
    0.06
    197
    0.06
    191
    0.06
    ERT
    0.06
    2
    0.06
    onas
    0.06
     Present
    0.06
    Activations Density 0.001%

    No Known Activations