© 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 EvalsExportsinterp-engineNEWAPI 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. 94629
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even"

    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
    ilan
    -0.08
    åŃĺäºİ
    -0.07
    $MESS
    -0.07
     lÃłng
    -0.06
    inus
    -0.06
    appings
    -0.06
    åĢī
    -0.06
    IMA
    -0.06
    ä¸įäºĨ
    -0.06
    è¼Ķ
    -0.06
    POSITIVE LOGITS
     when
    0.11
    when
    0.10
     if
    0.09
     když
    0.09
     wenn
    0.09
     khi
    0.08
     quando
    0.08
     cuando
    0.08
     jika
    0.07
     though
    0.07
    Activations Density 0.012%

    No Known Activations