© 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. 123486
    Prev
    Next
    INDEX
    Explanations

    terms related to censorship and restrictions on expression

    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
    åĦ¿
    -0.08
     tiên
    -0.07
    ly
    -0.06
    nels
    -0.06
    ulary
    -0.06
     sophistic
    -0.06
    éĥİ
    -0.06
    ernel
    -0.06
    stance
    -0.06
    alyzer
    -0.06
    POSITIVE LOGITS
    éĴ®
    0.07
    peria
    0.07
    ContentType
    0.06
    GLOBALS
    0.06
    æİī
    0.06
    oute
    0.06
    _exempt
    0.06
    vault
    0.06
    IOUS
    0.06
    itag
    0.06
    Activations Density 0.004%

    No Known Activations