© 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. 15-LLAMASCOPE-RES-131K
    6. 90273
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic policies and regulatory conditions

    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
     kaz
    -0.07
    á»ı
    -0.06
    uk
    -0.06
    عÙģ
    -0.06
    ι
    -0.06
    kah
    -0.06
     Kaz
    -0.06
    844
    -0.06
    ouz
    -0.06
    feld
    -0.06
    POSITIVE LOGITS
    elage
    0.09
     federal
    0.08
     public
    0.08
    åħ¬åħ±
    0.08
     öff
    0.08
    /Public
    0.07
     Federal
    0.07
    elpers
    0.07
     interstate
    0.07
    _tel
    0.07
    Activations Density 0.101%

    No Known Activations