© 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. 14093
    Prev
    Next
    INDEX
    Explanations

    academic-related terms, particularly those associated with theses and dissertations

    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
    inet
    -0.07
    iegel
    -0.06
    izik
    -0.06
     carc
    -0.05
    WHITE
    -0.05
     sole
    -0.05
     inject
    -0.05
    eral
    -0.05
    .onView
    -0.05
     gram
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.07
    .IContainer
    0.07
    alf
    0.07
    ORY
    0.06
    oker
    0.06
    ebi
    0.06
    <<<<
    0.06
    delay
    0.06
    paged
    0.06
    exus
    0.06
    Activations Density 0.001%

    No Known Activations