© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56208
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "have"

    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
    ano
    -0.07
    ien
    -0.07
     become
    -0.07
    бÑĥÑĢг
    -0.06
    ed
    -0.06
    aji
    -0.06
    enen
    -0.06
    inis
    -0.06
    ming
    -0.06
    å¾Ĺ
    -0.06
    POSITIVE LOGITS
    æk
    0.07
    'gc
    0.07
    quired
    0.06
    hold
    0.06
    ymous
    0.06
    ofs
    0.06
    ÏĦιÏĥ
    0.06
     Sür
    0.06
    สำ
    0.06
    à¥įतव
    0.06
    Activations Density 0.043%

    No Known Activations