© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119548
    Prev
    Next
    INDEX
    Explanations

    references to condominiums and related housing types

    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
    .scalablytyped
    -0.07
    ormsg
    -0.07
    OrDefault
    -0.07
    ilm
    -0.07
    wig
    -0.06
     conditioning
    -0.06
    ened
    -0.06
     Cust
    -0.06
    æĢ§çļĦ
    -0.06
    iences
    -0.06
    POSITIVE LOGITS
    /table
    0.07
    ů
    0.07
    -style
    0.07
    BCM
    0.07
    alte
    0.07
    Å¡tÄĽ
    0.07
    bers
    0.07
    itol
    0.07
    itori
    0.07
    latin
    0.07
    Activations Density 0.003%

    No Known Activations