© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121415
    Prev
    Next
    INDEX
    Explanations

    phrases related to oil extraction and environmental resource management

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    udd
    -0.05
     overall
    -0.05
     rov
    -0.05
     تÙģ
    -0.05
    /extensions
    -0.05
     Extension
    -0.05
    tach
    -0.05
    ATAL
    -0.05
    isu
    -0.05
     extended
    -0.05
    POSITIVE LOGITS
    uckle
    0.08
     Uploaded
    0.07
    éĢģ
    0.07
    odox
    0.07
    _uploaded
    0.07
     transportation
    0.07
     Marketable
    0.07
    -storage
    0.07
    è¾ĵ
    0.07
     transport
    0.07
    Activations Density 0.022%

    No Known Activations