© 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. 15-LLAMASCOPE-RES-131K
    11. 398
    Prev
    Next
    INDEX
    Explanations

    phrases indicating listings or occurrences 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
    ue
    -0.07
    ra
    -0.06
    nett
    -0.06
    itori
    -0.06
     Watt
    -0.06
    net
    -0.05
    elles
    -0.05
    uct
    -0.05
    cript
    -0.05
    ovo
    -0.05
    POSITIVE LOGITS
     defaultProps
    0.07
     fal
    0.07
    Observers
    0.07
     ><?
    0.07
    ิà¸įà¸į
    0.07
    »
    0.07
    oÄŁ
    0.07
    utos
    0.06
    ãĤĥ
    0.06
    canf
    0.06
    Activations Density 0.001%

    No Known Activations