© 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. 15-LLAMASCOPE-RES-131K
    11. 27655
    Prev
    Next
    INDEX
    Explanations

    phrases related to home repair services

    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
    /Branch
    -0.09
    ADDE
    -0.09
     nues
    -0.08
    åºŃ
    -0.08
    CTest
    -0.08
    LEAN
    -0.08
    rox
    -0.08
    krv
    -0.08
    Ìģt
    -0.08
    ̧
    -0.08
    POSITIVE LOGITS
    0.08
     c
    0.06
     ch
    0.06
     j
    0.06
     broken
    0.06
     sp
    0.06
     performed
    0.06
     any
    0.06
     p
    0.05
    oli
    0.05
    Activations Density 0.032%

    No Known Activations