© 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. 93751
    Prev
    Next
    INDEX
    Explanations

    terms related to insulation materials and their properties

    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
    abouts
    -0.08
    eny
    -0.08
    esh
    -0.07
    esses
    -0.07
    еÑĢк
    -0.07
    esis
    -0.06
    emer
    -0.06
    lum
    -0.06
    ationship
    -0.06
    åĿĽ
    -0.06
    POSITIVE LOGITS
     thickness
    0.08
    thickness
    0.08
    apiro
    0.07
     layers
    0.07
    mate
    0.07
    иÑĤив
    0.06
    ively
    0.06
    alah
    0.06
     layer
    0.06
     package
    0.06
    Activations Density 0.002%

    No Known Activations