© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78745
    Prev
    Next
    INDEX
    Explanations

    terms related to tax systems and classifications in a specific context

    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
    asio
    -0.08
    åħ¨åĽ½
    -0.07
    ovich
    -0.07
    entr
    -0.07
    SEL
    -0.07
     Herrera
    -0.06
    jong
    -0.06
     grav
    -0.06
    主任
    -0.06
    าà¸ĺ
    -0.06
    POSITIVE LOGITS
     overseas
    0.10
     foreign
    0.09
     abroad
    0.09
     Foreign
    0.08
     global
    0.07
    lobal
    0.07
    _foreign
    0.07
     foreigners
    0.07
     worldwide
    0.07
    浦
    0.07
    Activations Density 0.004%

    No Known Activations