© 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. 9-LLAMASCOPE-RES-131K
    11. 96422
    Prev
    Next
    INDEX
    Explanations

    phrases related to child protection and mental health issues

    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
    aji
    -0.07
    Ì
    -0.06
    onde
    -0.06
    bourg
    -0.06
    172
    -0.06
     affair
    -0.06
    RLF
    -0.06
     McGr
    -0.06
     Bent
    -0.05
    rouw
    -0.05
    POSITIVE LOGITS
    inspace
    0.07
    alink
    0.07
    apon
    0.07
    TextChanged
    0.07
     Pins
    0.07
    ä¹ħ
    0.06
    rat
    0.06
    é¾
    0.06
     gon
    0.06
    agrams
    0.06
    Activations Density 0.032%

    No Known Activations