© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    key terms related to data plans and telecom services

    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
    ragon
    -0.06
    wick
    -0.06
     tess
    -0.06
     envy
    -0.05
    uchos
    -0.05
    _EXTENDED
    -0.05
     Paren
    -0.05
     nomin
    -0.05
     squirt
    -0.05
     posts
    -0.05
    POSITIVE LOGITS
    ãĥªãĤ«
    0.08
    :UIAlert
    0.07
    reau
    0.07
     èģ
    0.07
    BoxLayout
    0.06
    京
    0.06
    md
    0.06
    roperty
    0.06
    aras
    0.06
    лл
    0.06
    Activations Density 0.001%

    No Known Activations