© 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. 1297
    Prev
    Next
    INDEX
    Explanations

    instances of personal reflection or subjective opinions

    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
     ISO
    -0.07
    ISO
    -0.07
     Scr
    -0.06
    28
    -0.06
     isolate
    -0.05
    983
    -0.05
    Verse
    -0.05
    adding
    -0.05
     slowly
    -0.05
    une
    -0.05
    POSITIVE LOGITS
    tips
    0.08
    emann
    0.08
     {?>↵
    0.08
    .removeListener
    0.08
    ulfilled
    0.07
    INCLUDED
    0.07
    klady
    0.07
     chapters
    0.07
    sled
    0.07
    ãĥ³ãĤ°ãĥ«
    0.07
    Activations Density 0.004%

    No Known Activations