© 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. 18667
    Prev
    Next
    INDEX
    Explanations

    topics related to political accountability and communication

    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
    etto
    -0.09
    isi
    -0.08
    õi
    -0.08
    ervo
    -0.08
    ernes
    -0.07
    odia
    -0.07
    andler
    -0.07
    ì»
    -0.07
    etect
    -0.07
     therap
    -0.07
    POSITIVE LOGITS
     constituents
    0.11
     constituent
    0.10
     constituency
    0.09
     district
    0.07
     Constit
    0.07
     my
    0.07
     Whip
    0.07
     office
    0.07
    0.06
     cas
    0.06
    Activations Density 0.057%

    No Known Activations