© 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. 17-LLAMASCOPE-RES-131K
    11. 85050
    Prev
    Next
    INDEX
    Explanations

    references to socioeconomic issues and the challenges faced by low-income individuals and families

    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
    linger
    -0.09
    loh
    -0.08
    ả
    -0.08
    obe
    -0.07
    ulan
    -0.07
    IRR
    -0.07
    anzi
    -0.07
    UBE
    -0.07
    upo
    -0.07
    acie
    -0.07
    POSITIVE LOGITS
     who
    0.08
     potential
    0.08
     segments
    0.07
     potentially
    0.07
     eligible
    0.07
     segment
    0.07
     indefinitely
    0.06
     нÑĥж
    0.06
    liers
    0.06
     missed
    0.06
    Activations Density 0.024%

    No Known Activations