© 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. 60521
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or groups in the context of scientific discussion

    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
    .ua
    -0.07
    esz
    -0.07
    ugins
    -0.07
    patible
    -0.07
     éĩ
    -0.07
    inha
    -0.06
    stime
    -0.06
    uben
    -0.06
    emsp
    -0.06
    adelphia
    -0.06
    POSITIVE LOGITS
    eec
    0.06
    sled
    0.06
    apur
    0.06
     ROOT
    0.06
     Pett
    0.06
     Uncategorized
    0.06
    VB
    0.06
    okoj
    0.06
     Cru
    0.05
    ckt
    0.05
    Activations Density 0.001%

    No Known Activations