© 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. 77873
    Prev
    Next
    INDEX
    Explanations

    phrases related to home inspections and detailed assessments of property 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
    agara
    -0.08
    bere
    -0.08
    beg
    -0.07
    bourg
    -0.07
    viar
    -0.07
    ικη
    -0.07
    Rendering
    -0.07
    yles
    -0.07
    ount
    -0.07
    asaki
    -0.07
    POSITIVE LOGITS
     seller
    0.09
     potential
    0.08
     Struct
    0.07
     BUY
    0.07
     transaction
    0.07
     Seller
    0.07
     inspection
    0.07
     sellers
    0.07
     Transaction
    0.07
     inherit
    0.06
    Activations Density 0.038%

    No Known Activations