© 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. 76765
    Prev
    Next
    INDEX
    Explanations

    adjectives and terms related to personalization and individual 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
    nte
    -0.07
    ayet
    -0.06
    FFE
    -0.06
    олеÑĤ
    -0.06
     news
    -0.06
    ILT
    -0.06
     sense
    -0.06
    iei
    -0.05
    ffi
    -0.05
    opper
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    istrovstvÃŃ
    0.08
    ButtonTitles
    0.07
    WidthSpace
    0.07
    ote
    0.07
    OffsetTable
    0.07
    ength
    0.07
     McDonald
    0.06
    kowski
    0.06
     ÑĤÑĢав
    0.06
    Activations Density 0.000%

    No Known Activations