© 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. 104039
    Prev
    Next
    INDEX
    Explanations

    repeated phrases indicating possession or association

    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
     же
    -0.08
    enk
    -0.08
    .scalablytyped
    -0.07
    HeaderCode
    -0.07
    imli
    -0.07
    ÄĽtÅ¡
    -0.07
    :normal
    -0.07
    ityEngine
    -0.07
    ocs
    -0.07
    FilterWhere
    -0.07
    POSITIVE LOGITS
    ach
    0.06
    SM
    0.06
    ana
    0.06
    asc
    0.06
    venue
    0.05
    ART
    0.05
    ape
    0.05
    artment
    0.05
    bere
    0.05
     propor
    0.05
    Activations Density 0.059%

    No Known Activations