© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 124008
    Prev
    Next
    INDEX
    Explanations

    concepts related to diversity and equality

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    hatt
    -0.07
    oji
    -0.06
    âĢİ
    -0.06
    amaz
    -0.06
     aff
    -0.06
     док
    -0.06
     att
    -0.06
    kus
    -0.05
    acht
    -0.05
    aeda
    -0.05
    POSITIVE LOGITS
    ɵ
    0.08
    ubat
    0.07
    atoire
    0.06
    icions
    0.06
    yonel
    0.06
    Łèĥ½
    0.06
     è¨Ģ
    0.06
     Pap
    0.06
    744
    0.06
    736
    0.06
    Activations Density 0.000%

    No Known Activations