© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 85019
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to regulatory obligations and conditions affecting children's welfare

    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
    ÑĤи
    -0.06
     Gardner
    -0.06
     Haven
    -0.06
    haven
    -0.06
     Habit
    -0.06
    tü
    -0.06
     oblig
    -0.06
    484
    -0.05
    DT
    -0.05
     net
    -0.05
    POSITIVE LOGITS
    zoek
    0.08
     bona
    0.07
    aget
    0.07
     insign
    0.07
    agher
    0.07
     merely
    0.07
     Minor
    0.07
    νι
    0.07
    nodoc
    0.07
    meer
    0.07
    Activations Density 0.008%

    No Known Activations