© 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. 17655
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and significant life events

    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
    regor
    -0.08
    Ø®ÙĪاÙĨ
    -0.07
     permanently
    -0.07
    egen
    -0.07
     slowly
    -0.06
    Ä©
    -0.06
    å¼ĺ
    -0.06
    ÙĥÙĬØ©
    -0.06
    lea
    -0.06
    fax
    -0.06
    POSITIVE LOGITS
     consecutive
    0.14
     consec
    0.11
     successive
    0.09
     within
    0.08
    åIJĮãģĺ
    0.08
     consect
    0.08
    è¿ŀ
    0.07
    within
    0.07
    estro
    0.07
     sequential
    0.07
    Activations Density 0.033%

    No Known Activations