© 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. 22-LLAMASCOPE-RES-131K
    11. 4025
    Prev
    Next
    INDEX
    Explanations

    expressions of disbelief or incredulity

    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
    Ø´ÙĪر
    -0.07
    acman
    -0.07
    .glide
    -0.07
    .unknown
    -0.07
    ä¿
    -0.07
    èĬ
    -0.07
    ë¹
    -0.07
    /umd
    -0.07
    unky
    -0.07
     Impress
    -0.07
    POSITIVE LOGITS
     disbelief
    0.16
     believe
    0.15
     belief
    0.15
     believing
    0.14
    belie
    0.14
     believed
    0.13
     unbelievable
    0.13
     Believe
    0.13
    belief
    0.13
     believes
    0.12
    Activations Density 0.027%

    No Known Activations