Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43457
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to real estate and lawyer listings

    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
     tvar
    -0.07
    ơi
    -0.06
    OOT
    -0.06
    eldom
    -0.06
     mark
    -0.06
    _attach
    -0.06
    .pkg
    -0.06
    orno
    -0.06
     roÄįnÃŃ
    -0.06
     Tablets
    -0.06
    POSITIVE LOGITS
     listings
    0.42
     listing
    0.41
     listed
    0.39
     Listing
    0.35
    Listing
    0.35
     Listings
    0.34
    listing
    0.32
    listed
    0.31
     Listed
    0.30
    _listing
    0.28
    Activations Density 0.012%

    No Known Activations