© 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. 116356
    Prev
    Next
    INDEX
    Explanations

    phrases about labor unions and solidarity

    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
    fet
    -0.06
     pron
    -0.06
     ex
    -0.06
     peg
    -0.06
    vid
    -0.05
    sect
    -0.05
     self
    -0.05
    eg
    -0.05
    rien
    -0.05
     hunger
    -0.05
    POSITIVE LOGITS
    adu
    0.09
     action
    0.08
     Thur
    0.07
    íĦ
    0.07
    ocale
    0.07
     Action
    0.07
    ãģĭãģªãģĦ
    0.07
    lamaz
    0.07
    Uvs
    0.07
     ACTION
    0.07
    Activations Density 0.017%

    No Known Activations