© 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. 22-LLAMASCOPE-RES-131K
    11. 3893
    Prev
    Next
    INDEX
    Explanations

    references to people and communities affected by services or policies

    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
     highway
    -0.07
    INTEGER
    -0.07
     highways
    -0.07
    vendor
    -0.06
     bridge
    -0.06
    æģ¯
    -0.06
    bridge
    -0.06
     boys
    -0.06
     Highway
    -0.06
    ibi
    -0.06
    POSITIVE LOGITS
     households
    0.15
     household
    0.14
     residential
    0.12
     customers
    0.12
     homes
    0.12
    customers
    0.11
     premises
    0.11
    家åºŃ
    0.11
     Customers
    0.10
     consumers
    0.10
    Activations Density 0.033%

    No Known Activations