© 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. 108801
    Prev
    Next
    INDEX
    Explanations

    references to travel-related amenities and experiences

    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
     Mercer
    -0.07
    lotte
    -0.06
    aison
    -0.06
    adder
    -0.06
    NI
    -0.06
     arson
    -0.06
    andan
    -0.06
     Swe
    -0.06
    .must
    -0.06
     driveway
    -0.05
    POSITIVE LOGITS
     passengers
    0.10
     seat
    0.09
    Seat
    0.08
    irlines
    0.08
     Seat
    0.08
     Passenger
    0.08
     hÃłnh
    0.07
     passenger
    0.07
    -seat
    0.07
    æķ¦
    0.07
    Activations Density 0.020%

    No Known Activations