© 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. 15-LLAMASCOPE-RES-131K
    11. 85995
    Prev
    Next
    INDEX
    Explanations

    topics related to social justice and advocacy 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
    ataka
    -0.07
    IRTH
    -0.07
    .criteria
    -0.06
    alara
    -0.06
    ÏĢοιη
    -0.06
     kontro
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
     же
    -0.06
    imple
    -0.06
    impl
    -0.06
    POSITIVE LOGITS
    probe
    0.06
     probe
    0.06
    haft
    0.06
    езд
    0.06
     haz
    0.06
    á»ĩ
    0.06
     Hundred
    0.06
    fy
    0.06
    0.06
    å°ļ
    0.06
    Activations Density 0.048%

    No Known Activations