© 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. 29767
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal procedures and considerations

    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
    .raises
    -0.07
    onom
    -0.07
    opped
    -0.07
    eton
    -0.07
     Ùħض
    -0.07
    exion
    -0.06
    кÑĸв
    -0.06
    är
    -0.06
    rome
    -0.06
    ped
    -0.06
    POSITIVE LOGITS
     bias
    0.08
     prejud
    0.07
     Bias
    0.07
     contamination
    0.07
     impartial
    0.07
     influences
    0.07
     pre
    0.07
     Equity
    0.06
     biases
    0.06
     Cherry
    0.06
    Activations Density 0.007%

    No Known Activations