© 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. 84264
    Prev
    Next
    INDEX
    Explanations

    phrases related to laying foundations or groundwork for projects or ideas

    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
    ÄĽ
    -0.07
    ÑĢог
    -0.07
    asion
    -0.07
    Äĩ
    -0.06
    eland
    -0.06
    zag
    -0.06
    iej
    -0.06
    کرد
    -0.06
    sı
    -0.06
    cil
    -0.06
    POSITIVE LOGITS
     laid
    0.12
     lays
    0.11
     groundwork
    0.11
     lay
    0.10
     laying
    0.10
     Lay
    0.10
    lay
    0.09
     foundation
    0.09
     foundations
    0.08
    acker
    0.08
    Activations Density 0.015%

    No Known Activations