© 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. 27633
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal concepts and their implications

    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
     kostenlose
    -0.07
    ãĨ
    -0.07
    CLUDING
    -0.06
     DropIndex
    -0.06
    /releases
    -0.06
    âĢª
    -0.06
     zav
    -0.06
    _prec
    -0.06
     nederland
    -0.06
    remember
    -0.06
    POSITIVE LOGITS
     patterns
    0.16
     pattern
    0.15
     Patterns
    0.14
     trends
    0.13
    pattern
    0.12
    patterns
    0.12
     Pattern
    0.12
     emerg
    0.12
    Patterns
    0.11
    -pattern
    0.11
    Activations Density 0.120%

    No Known Activations