© 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. 27057
    Prev
    Next
    INDEX
    Explanations

    concerns related to government regulations and societal justice issues

    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
    Å¡ak
    -0.08
    NONE
    -0.07
    astle
    -0.07
    ~/
    -0.06
    -haspopup
    -0.06
    atsu
    -0.06
    INVAL
    -0.06
    rought
    -0.06
    -↵
    -0.06
    rowse
    -0.06
    POSITIVE LOGITS
     ‘
    0.09
     '
    0.09
     '(
    0.07
     intl
    0.07
    ittle
    0.07
     &#
    0.07
     «
    0.06
    vt
    0.06
    ertext
    0.06
    esimal
    0.06
    Activations Density 0.092%

    No Known Activations