© 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. 75847
    Prev
    Next
    INDEX
    Explanations

    concepts related to housing affordability and economic 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
    Äįer
    -0.08
    ]={↵
    -0.07
    /tiny
    -0.07
    USED
    -0.07
    .Areas
    -0.07
    umblr
    -0.07
     ifdef
    -0.07
    ipay
    -0.06
     audition
    -0.06
     Hotels
    -0.06
    POSITIVE LOGITS
     median
    0.07
     decent
    0.07
    Latch
    0.07
     Median
    0.07
     Crime
    0.07
     crime
    0.07
    tu
    0.07
    ighbor
    0.07
     rootNode
    0.06
    median
    0.06
    Activations Density 0.010%

    No Known Activations