© 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. 94187
    Prev
    Next
    INDEX
    Explanations

    real estate features and qualities in property descriptions

    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
    ÏĢή
    -0.08
    èĵ
    -0.07
    ertools
    -0.07
    коÑĤ
    -0.06
    ear
    -0.06
    gw
    -0.06
     Mechanics
    -0.06
    chyb
    -0.06
    igg
    -0.06
    kan
    -0.06
    POSITIVE LOGITS
     equity
    0.06
     Equ
    0.06
     equipped
    0.06
     Bath
    0.06
     bath
    0.06
    ÑĢем
    0.06
    readcr
    0.06
    GetData
    0.06
     equiv
    0.05
    /utility
    0.05
    Activations Density 0.004%

    No Known Activations