© 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. 17-LLAMASCOPE-RES-131K
    11. 17764
    Prev
    Next
    INDEX
    Explanations

    legal challenges related to firearms and their taxation

    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
    leon
    -0.07
    avad
    -0.07
    éħĴ
    -0.06
    ictim
    -0.06
    पत
    -0.06
    .rpc
    -0.06
    urst
    -0.06
     caucus
    -0.06
    .heroku
    -0.06
    å¹ħ
    -0.06
    POSITIVE LOGITS
     court
    0.10
     challenge
    0.09
    court
    0.09
     Supreme
    0.08
     lawsuit
    0.08
    ourt
    0.08
     lawsuits
    0.07
     Court
    0.07
     challenges
    0.07
     sue
    0.07
    Activations Density 0.106%

    No Known Activations