© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75724
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to court rulings and evidence

    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
    æĴ
    -0.07
    blas
    -0.07
    ActionResult
    -0.07
     Král
    -0.06
    áºŃu
    -0.06
    Ð¤ÐĽ
    -0.06
     oku
    -0.06
    reed
    -0.06
    alu
    -0.06
    omu
    -0.06
    POSITIVE LOGITS
     submissions
    0.07
    umeric
    0.06
     turret
    0.06
     Pony
    0.06
    거리
    0.06
     submit
    0.06
     Submission
    0.06
     raised
    0.06
     during
    0.06
    129
    0.06
    Activations Density 0.016%

    No Known Activations