© 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. 127434
    Prev
    Next
    INDEX
    Explanations

    instances of recognition or acknowledgment of characters and archetypes

    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
    .Contract
    -0.07
    isper
    -0.07
    usz
    -0.06
    reich
    -0.06
    ardy
    -0.06
    enn
    -0.06
    emet
    -0.06
     Role
    -0.06
    IOUS
    -0.06
     visibility
    -0.06
    POSITIVE LOGITS
     instantly
    0.09
    recogn
    0.08
    enville
    0.08
     immediately
    0.07
     recognizable
    0.07
     recognize
    0.07
     familiar
    0.07
     Recogn
    0.07
    ¢åįķ
    0.07
    ÙĦØŃ
    0.07
    Activations Density 0.008%

    No Known Activations