© 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. 126573
    Prev
    Next
    INDEX
    Explanations

    phrases related to liability and responsibility

    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
    elder
    -0.08
    çĤ
    -0.07
    phis
    -0.07
    ahat
    -0.07
    год
    -0.06
     '&#
    -0.06
    tridges
    -0.06
    ibase
    -0.06
    arrera
    -0.06
    ÑģÑĤÑĢой
    -0.06
    POSITIVE LOGITS
    çĶ¨æĪ·
    0.08
     customers
    0.07
     you
    0.07
     users
    0.07
     individuals
    0.07
     Individuals
    0.06
     Users
    0.06
     usuário
    0.06
     çĶ¨æĪ·
    0.06
    олÑĮзоваÑĤ
    0.06
    Activations Density 0.008%

    No Known Activations