© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 56279
    Prev
    Next
    INDEX
    Explanations

    references to potty training and associated behaviors

    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
    anco
    -0.07
    .LookAndFeel
    -0.07
    anja
    -0.06
    ä¹İ
    -0.06
    æı
    -0.06
    ipar
    -0.06
     minib
    -0.06
    αι
    -0.06
     Vuex
    -0.06
     Essential
    -0.06
    POSITIVE LOGITS
     bladder
    0.10
     volume
    0.07
    érie
    0.07
    _volume
    0.07
     urgency
    0.07
     flex
    0.07
     urinary
    0.07
     capacity
    0.07
    affer
    0.07
    Volume
    0.07
    Activations Density 0.037%

    No Known Activations