© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 94434
    Prev
    Next
    INDEX
    Explanations

    phrases related to child independence and safety concerns

    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
    ÑĢÑĮ
    -0.07
    engin
    -0.07
     Bracket
    -0.07
    riba
    -0.07
    cales
    -0.06
    angen
    -0.06
    nk
    -0.06
    ÑĮв
    -0.06
    Bracket
    -0.06
    uml
    -0.06
    POSITIVE LOGITS
     independence
    0.12
     Independence
    0.11
     independently
    0.10
    Independ
    0.10
     independent
    0.10
    çĭ¬ç«ĭ
    0.09
    Independent
    0.09
     ÑģамоÑģÑĤ
    0.09
     Independ
    0.08
     ÑģамоÑģÑĤоÑıÑĤелÑĮ
    0.08
    Activations Density 0.006%

    No Known Activations