© 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. 16856
    Prev
    Next
    INDEX
    Explanations

    features and amenities related to real estate properties

    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
    tÃŃ
    -0.07
     Pornhub
    -0.07
    .scalablytyped
    -0.07
    104
    -0.07
     Majority
    -0.07
     DISCLAIM
    -0.06
     majority
    -0.06
     cdecl
    -0.06
    etta
    -0.06
    .infinity
    -0.06
    POSITIVE LOGITS
    iali
    0.08
    olle
    0.07
    emem
    0.07
    oron
    0.06
     integrated
    0.06
    detach
    0.06
    prov
    0.06
    eller
    0.06
    pais
    0.06
    رÙģ
    0.06
    Activations Density 0.004%

    No Known Activations