© 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 EvalsExportsinterp-engineNEWAPI 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. 79962
    Prev
    Next
    INDEX
    Explanations

    aspects related to seating and space in vehicles

    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
    akis
    -0.08
     ConnectionState
    -0.07
    _HERSHEY
    -0.07
    IDA
    -0.07
    .jdesktop
    -0.07
     첨ë¶Ģ
    -0.07
    lotte
    -0.07
    ÅĻit
    -0.07
     zipfile
    -0.07
     ActiveForm
    -0.07
    POSITIVE LOGITS
     rear
    0.10
     seats
    0.09
     seat
    0.07
    rear
    0.07
    olie
    0.07
    -seat
    0.07
     Seats
    0.07
     Rear
    0.06
     positions
    0.06
     cargo
    0.06
    Activations Density 0.005%

    No Known Activations