© 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. 105699
    Prev
    Next
    INDEX
    Explanations

    information related to child neglect or abuse cases

    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
    .constructor
    -0.07
    ìłķìĿ´
    -0.07
    urette
    -0.07
    коз
    -0.07
    Ïħν
    -0.07
     اÙĦخط
    -0.07
    rrha
    -0.07
    mojom
    -0.07
    duk
    -0.07
     flood
    -0.07
    POSITIVE LOGITS
     neglect
    0.07
     child
    0.07
     Child
    0.06
     Children
    0.06
    ished
    0.06
     children
    0.06
     parenting
    0.06
    Neg
    0.05
     allegedly
    0.05
    annis
    0.05
    Activations Density 0.013%

    No Known Activations