© 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. 61490
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate satisfaction or recommendation regarding services, particularly home inspection

    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
    ÑģÑıÑĤ
    -0.06
    lease
    -0.06
     вÑĭп
    -0.06
    enti
    -0.06
    ucas
    -0.06
    elage
    -0.06
    eparator
    -0.06
    EMA
    -0.06
    388
    -0.06
    éĥ
    -0.06
    POSITIVE LOGITS
     defects
    0.08
     inspections
    0.07
    REA
    0.06
    çĶ²
    0.06
    /report
    0.06
     Inspection
    0.06
     Report
    0.06
     performed
    0.06
     condominium
    0.06
     defect
    0.06
    Activations Density 0.107%

    No Known Activations