© 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 EvalsExportsAPI 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. 86169
    Prev
    Next
    INDEX
    Explanations

    references to meal settings and communal dining experiences

    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
     bake
    -0.07
     Bake
    -0.07
    iolet
    -0.06
    dispatch
    -0.06
     ramp
    -0.06
    amental
    -0.06
     Boot
    -0.06
    presso
    -0.05
     dispatch
    -0.05
     rent
    -0.05
    POSITIVE LOGITS
     table
    0.10
     forks
    0.09
     TABLE
    0.09
    .table
    0.08
    ewis
    0.08
    -table
    0.08
     Dining
    0.08
     Table
    0.08
     dining
    0.08
    polator
    0.08
    Activations Density 0.026%

    No Known Activations