© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95897
    Prev
    Next
    INDEX
    Explanations

    references to sculpture and sculptors

    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
    apore
    -0.07
    zdy
    -0.07
    croft
    -0.07
    åıĤä¸İ
    -0.07
    omor
    -0.07
    .UIManager
    -0.07
    ocus
    -0.07
    ondo
    -0.06
    Uvs
    -0.06
    ãĥ¼ãĥĨ
    -0.06
    POSITIVE LOGITS
    soap
    0.06
    èĤĮ
    0.06
     Grants
    0.06
     soap
    0.06
    ahat
    0.06
    äºĴ
    0.06
    .setDefault
    0.06
     desn
    0.06
     sculpt
    0.06
     soc
    0.05
    Activations Density 0.008%

    No Known Activations