© 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. 14946
    Prev
    Next
    INDEX
    Explanations

    details related to car specifications and pricing

    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
    .TryParse
    -0.07
    abant
    -0.07
    lide
    -0.06
     Pitch
    -0.06
     Recommended
    -0.06
     Cater
    -0.06
    dz
    -0.06
    aine
    -0.06
     pitches
    -0.06
    appe
    -0.06
    POSITIVE LOGITS
     Rum
    0.07
    andel
    0.07
     expect
    0.07
     Kelley
    0.06
     expectation
    0.06
    eed
    0.06
     Renders
    0.06
    expect
    0.06
    rum
    0.06
    renders
    0.06
    Activations Density 0.005%

    No Known Activations