© 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 EvalsExportsAPI 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. 57306
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and property renovations

    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
    εβ
    -0.08
    .BL
    -0.06
    _runtime
    -0.06
    iations
    -0.06
     retr
    -0.06
    weg
    -0.06
    inters
    -0.06
    ritable
    -0.06
    alm
    -0.06
     reservations
    -0.06
    POSITIVE LOGITS
    ä¿®
    0.10
     structural
    0.10
     projects
    0.10
     fixes
    0.10
     project
    0.09
     improvements
    0.09
     Projects
    0.09
     repairs
    0.09
     renovation
    0.09
     Fix
    0.09
    Activations Density 0.282%

    No Known Activations