© 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. 27081
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintaining consistency and communication

    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
    andin
    -0.07
    jabi
    -0.07
    linger
    -0.06
    bst
    -0.06
    hung
    -0.06
    ppv
    -0.06
    udev
    -0.06
    ünd
    -0.06
     cellForRowAt
    -0.06
    achte
    -0.06
    POSITIVE LOGITS
    å¹³æĪIJ
    0.07
    .mapping
    0.06
    /respond
    0.06
    ucs
    0.06
    æݪ
    0.06
    heck
    0.06
    .sharedInstance
    0.06
     gol
    0.06
    ëĦ·
    0.06
    olia
    0.06
    Activations Density 0.006%

    No Known Activations