© 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. 77975
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations and policies

    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
    Accessory
    -0.07
    åł
    -0.07
    [@
    -0.07
    vell
    -0.07
    .idea
    -0.07
    MediaType
    -0.07
    .Serial
    -0.07
     bì
    -0.07
    ãĥ©ãĥĥãĤ¯
    -0.07
    acket
    -0.07
    POSITIVE LOGITS
     Regulation
    0.06
     Operators
    0.06
     Dems
    0.06
    zew
    0.06
     operator
    0.06
     data
    0.06
    -data
    0.05
     komm
    0.05
     social
    0.05
    444
    0.05
    Activations Density 0.001%

    No Known Activations