© 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. 125795
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial transactions or exchanges

    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
     Aware
    -0.07
    illet
    -0.06
    ikut
    -0.06
    åĪ°äºĨ
    -0.06
     threw
    -0.06
    vit
    -0.06
    lette
    -0.06
    isay
    -0.06
    XR
    -0.06
    sei
    -0.06
    POSITIVE LOGITS
    ereo
    0.07
    yd
    0.07
    ero
    0.07
    ahoo
    0.06
    ño
    0.06
     Cum
    0.06
    ableView
    0.06
    olar
    0.06
    athan
    0.06
    åħ³
    0.06
    Activations Density 0.003%

    No Known Activations