© 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. 70160
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to laws or regulations

    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
    efon
    -0.07
    Ñĥмов
    -0.07
    amat
    -0.06
    olk
    -0.06
     zich
    -0.06
    εÏħ
    -0.06
    ειÏĤ
    -0.06
     porad
    -0.06
    ç»Ń
    -0.06
    ron
    -0.06
    POSITIVE LOGITS
     laws
    0.07
     Laws
    0.07
     Neville
    0.07
    istry
    0.07
    vailable
    0.06
    ãĥ¼ãĥį
    0.06
    laws
    0.06
    ุà¸ĩ
    0.06
     Ere
    0.06
    afs
    0.06
    Activations Density 0.002%

    No Known Activations