© 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. 74933
    Prev
    Next
    INDEX
    Explanations

    items related to kitchen and bathroom fixtures, particularly different types of countertops

    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
    otu
    -0.06
    reed
    -0.06
    udes
    -0.06
    åĪº
    -0.06
    bird
    -0.06
    allel
    -0.06
    opr
    -0.06
    wig
    -0.06
    textTheme
    -0.05
     att
    -0.05
    POSITIVE LOGITS
    ehler
    0.07
    sWith
    0.07
    steen
    0.07
     surfaces
    0.07
    subst
    0.07
    arga
    0.07
    Kitchen
    0.07
     chảy
    0.07
    عاÙĦ
    0.07
     surface
    0.06
    Activations Density 0.006%

    No Known Activations