© 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. 5-LLAMASCOPE-RES-131K
    11. 125852
    Prev
    Next
    INDEX
    Explanations

    references to Polish culture or topics

    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
    icap
    -0.08
    rema
    -0.08
    iest
    -0.08
    ipc
    -0.07
    opal
    -0.07
    /out
    -0.07
    nut
    -0.07
    Ùİع
    -0.07
    using
    -0.07
    osaur
    -0.07
    POSITIVE LOGITS
    atr
    0.07
    ajes
    0.06
    anzi
    0.06
     tinh
    0.06
    innacle
    0.06
    abbrev
    0.06
    ãĥĥãĥī
    0.06
    ÙħÛĮ
    0.06
    Instr
    0.06
    lient
    0.06
    Activations Density 0.011%

    No Known Activations