© 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. 119754
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to emotional responses and reflections

    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
    okino
    -0.07
    irq
    -0.07
    ')==
    -0.07
    vÄĽ
    -0.07
    ког
    -0.07
    ожеÑĤ
    -0.07
     Voll
    -0.07
    UNCH
    -0.06
    è§
    -0.06
    cheid
    -0.06
    POSITIVE LOGITS
     type
    0.10
     kind
    0.09
    type
    0.08
    -type
    0.08
     syndrome
    0.07
     scenario
    0.07
    kind
    0.07
     scenarios
    0.07
     kinda
    0.07
    idden
    0.06
    Activations Density 0.030%

    No Known Activations