© 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. 31586
    Prev
    Next
    INDEX
    Explanations

    terms associated with the legalization of marijuana and its legal status

    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
    rix
    -0.07
    eldo
    -0.06
    leh
    -0.06
    lesson
    -0.06
    лоп
    -0.06
    CDF
    -0.06
    eworld
    -0.06
    RIX
    -0.06
     Wahl
    -0.06
    Alle
    -0.06
    POSITIVE LOGITS
    ãĤº
    0.07
    atures
    0.07
    iferay
    0.07
    /legal
    0.07
    Ø´ÙĨ
    0.07
    searchModel
    0.06
    /prom
    0.06
    amba
    0.06
    istrator
    0.06
    $MESS
    0.06
    Activations Density 0.004%

    No Known Activations