© 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. 123593
    Prev
    Next
    INDEX
    Explanations

    instances of legal or regulatory accountability

    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
     trùng
    -0.06
    CLAIM
    -0.06
     Offensive
    -0.06
    -----------*/↵
    -0.06
    RIORITY
    -0.05
     Dou
    -0.05
    anlık
    -0.05
     Singles
    -0.05
    eded
    -0.05
    èħ¿
    -0.05
    POSITIVE LOGITS
     impe
    0.10
     impeachment
    0.09
     Tud
    0.07
     removal
    0.07
    ozem
    0.07
     grounds
    0.07
    -remove
    0.07
    remove
    0.07
    mrt
    0.07
    aticon
    0.07
    Activations Density 0.010%

    No Known Activations