© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126586
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to laws and offenses

    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
    amburger
    -0.07
     Scot
    -0.07
    inds
    -0.07
    icter
    -0.06
    levator
    -0.06
    ehler
    -0.06
    asin
    -0.06
    ustin
    -0.06
    298
    -0.06
    ÃŃn
    -0.06
    POSITIVE LOGITS
    ONTAL
    0.09
    anken
    0.07
    ront
    0.07
    ocos
    0.07
    README
    0.06
     Moj
    0.06
    oons
    0.06
    iliz
    0.06
     Westbrook
    0.06
    iline
    0.06
    Activations Density 0.133%

    No Known Activations