© 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. 75012
    Prev
    Next
    INDEX
    Explanations

    references to parental organizations and their activities related to school policies

    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
     trainer
    -0.06
     clients
    -0.06
    ipo
    -0.06
     mentor
    -0.06
    anga
    -0.06
    udson
    -0.06
    _browser
    -0.06
    trainer
    -0.06
     Trainer
    -0.06
     Clients
    -0.06
    POSITIVE LOGITS
    oplan
    0.07
    à¤Ĥधन
    0.07
    AccessorType
    0.07
    spender
    0.07
     DISCLAIM
    0.07
    communication
    0.06
    illac
    0.06
    arent
    0.06
    meden
    0.06
    ERT
    0.06
    Activations Density 0.004%

    No Known Activations