© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 77192
    Prev
    Next
    INDEX
    Explanations

    statements related to government and community assistance issues

    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
    quier
    -0.08
    ç³»
    -0.08
     globals
    -0.08
     RTBU
    -0.07
    áÄį
    -0.07
     rekl
    -0.07
    ãģıãģł
    -0.07
    á»įt
    -0.07
    encode
    -0.07
     sơ
    -0.07
    POSITIVE LOGITS
     economic
    0.10
     infra
    0.10
     development
    0.09
     developmental
    0.09
     infrastructure
    0.09
     Development
    0.09
    -development
    0.08
     improvement
    0.08
    development
    0.08
     Economic
    0.08
    Activations Density 0.072%

    No Known Activations