© 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. 70509
    Prev
    Next
    INDEX
    Explanations

    concepts related to data matching and record linkage in statistical contexts

    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
    ãĥĥãĥī
    -0.08
    aeper
    -0.07
    -pocket
    -0.07
    åij¨å¹´
    -0.06
    allis
    -0.06
    lam
    -0.06
    æľĭ
    -0.06
    eyen
    -0.06
    ÑĪÑĮ
    -0.06
    engin
    -0.06
    POSITIVE LOGITS
    associate
    0.07
     corresponding
    0.07
     associate
    0.07
     identity
    0.07
     match
    0.07
     records
    0.07
     record
    0.07
     identification
    0.07
     associated
    0.07
     assoc
    0.07
    Activations Density 0.022%

    No Known Activations