© 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. 5-LLAMASCOPE-RES-131K
    11. 125398
    Prev
    Next
    INDEX
    Explanations

    references to issues related to flooding and property protection

    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
    oram
    -0.07
    _hub
    -0.06
    ID
    -0.06
     roofs
    -0.06
     Ents
    -0.06
    elman
    -0.06
     Flags
    -0.06
    ãĥ¼ãĥ³
    -0.06
    Hub
    -0.06
     Hanna
    -0.06
    POSITIVE LOGITS
    _VENDOR
    0.07
    rooms
    0.07
    esta
    0.07
     æ¸
    0.07
    arie
    0.06
     SAR
    0.06
     Glide
    0.06
     presence
    0.06
    .Selenium
    0.06
     sar
    0.06
    Activations Density 0.006%

    No Known Activations