© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116632
    Prev
    Next
    INDEX
    Explanations

    references to relationships or familial connections

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    usi
    -0.07
    üf
    -0.07
    ediator
    -0.07
    ,[],
    -0.07
    üss
    -0.06
    .scalablytyped
    -0.06
     =>$
    -0.06
    ť
    -0.06
    ,:,
    -0.06
     menstr
    -0.06
    POSITIVE LOGITS
     scrim
    0.06
    Ä©
    0.06
    iative
    0.06
    ¸
    0.06
     Overwatch
    0.06
     ([[
    0.05
    _construct
    0.05
    leaf
    0.05
    a
    0.05
    oin
    0.05
    Activations Density 0.012%

    No Known Activations