© 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. 91533
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of home decor and design elements

    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
     record
    -0.06
    .svg
    -0.06
    uly
    -0.06
     çĻº
    -0.06
    icut
    -0.06
     mapping
    -0.06
     kå
    -0.06
     constructs
    -0.06
    umhur
    -0.06
     wc
    -0.05
    POSITIVE LOGITS
    iac
    0.07
    .install
    0.07
     hanging
    0.07
     Addison
    0.07
     tub
    0.07
     (~(
    0.06
    rooms
    0.06
     spol
    0.06
    enze
    0.06
     addition
    0.06
    Activations Density 0.033%

    No Known Activations