© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 93835
    Prev
    Next
    INDEX
    Explanations

    phrases related to repair and maintenance 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
    istrovstvÃŃ
    -0.08
    ĺ认
    -0.07
     Harness
    -0.07
    ãĤ¤ãĥĦ
    -0.07
    UNET
    -0.07
     kabil
    -0.07
    dob
    -0.07
    enty
    -0.07
    ADDE
    -0.06
    PRETTY
    -0.06
    POSITIVE LOGITS
     restoring
    0.07
     restores
    0.07
     fast
    0.06
    enschaft
    0.06
     problem
    0.06
     affordable
    0.06
     FAST
    0.06
    ůj
    0.06
     repar
    0.06
     restored
    0.06
    Activations Density 0.025%

    No Known Activations