© 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. 28267
    Prev
    Next
    INDEX
    Explanations

    legal references and citations from judicial opinions

    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
     forth
    -0.07
    PTH
    -0.07
    ypo
    -0.07
    olicited
    -0.06
     ext
    -0.06
     conver
    -0.06
     cen
    -0.06
     cle
    -0.05
    uda
    -0.05
     Mao
    -0.05
    POSITIVE LOGITS
    braco
    0.08
    orado
    0.08
    먼
    0.07
    istrovstvÃŃ
    0.07
    üss
    0.07
    actionDate
    0.07
    ãĥ¼ãĥł
    0.07
    .scalablytyped
    0.07
    FromClass
    0.07
     aime
    0.07
    Activations Density 0.015%

    No Known Activations