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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 78957
    Prev
    Next
    INDEX
    Explanations

    references to wealth and affluent individuals

    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
     AppState
    -0.07
    že
    -0.07
    jang
    -0.07
    ald
    -0.06
    uild
    -0.06
    ists
    -0.06
    cean
    -0.06
    eds
    -0.06
    gle
    -0.06
    aran
    -0.06
    POSITIVE LOGITS
    /power
    0.07
     Enough
    0.07
    (er
    0.07
     richer
    0.07
    /generated
    0.07
     enough
    0.07
    rich
    0.07
    esses
    0.07
    ness
    0.07
    ened
    0.07
    Activations Density 0.008%

    No Known Activations