© 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. 80519
    Prev
    Next
    INDEX
    Explanations

    information related to airline loyalty programs and the earning of reward miles

    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
    моÑģ
    -0.07
    alley
    -0.07
    èī¦
    -0.07
    MLS
    -0.07
    STYPE
    -0.07
    ReadWrite
    -0.06
    aed
    -0.06
     atd
    -0.06
    á»ijng
    -0.06
    élé
    -0.06
    POSITIVE LOGITS
     destinations
    0.14
     destination
    0.10
     trip
    0.10
     trips
    0.10
    _destination
    0.09
     Dest
    0.09
    dest
    0.09
     journey
    0.09
     routes
    0.09
    destination
    0.09
    Activations Density 0.107%

    No Known Activations