© 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. 9-LLAMASCOPE-RES-131K
    11. 98439
    Prev
    Next
    INDEX
    Explanations

    phrases expressing disdain or criticism towards certain groups or 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
     equally
    -0.06
    åįĪ
    -0.06
    RowAt
    -0.06
    ListOf
    -0.06
     Siege
    -0.06
     rav
    -0.06
     Lump
    -0.06
     McGu
    -0.06
    ishi
    -0.05
     Blo
    -0.05
    POSITIVE LOGITS
     Anonymous
    0.07
    幸
    0.06
    999
    0.06
    оÑĢаз
    0.06
     Ply
    0.06
    ract
    0.06
    457
    0.06
    abled
    0.06
    ucky
    0.06
     fate
    0.06
    Activations Density 0.011%

    No Known Activations