© 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 EvalsExportsinterp-engineNEWAPI 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. 104967
    Prev
    Next
    INDEX
    Explanations

    words related to growth and development

    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
     вÑģÑĤ
    -0.06
    iry
    -0.06
    kov
    -0.06
    .ObjectModel
    -0.06
    unu
    -0.06
    ieri
    -0.06
     Mellon
    -0.06
     erh
    -0.06
     basics
    -0.06
    ect
    -0.06
    POSITIVE LOGITS
    iller
    0.07
    pte
    0.06
    Äĩe
    0.06
    iov
    0.06
    TRL
    0.06
    semicolon
    0.06
    ibar
    0.06
     forget
    0.06
    į
    0.06
    abin
    0.06
    Activations Density 0.012%

    No Known Activations