© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 27164
    Prev
    Next
    INDEX
    Explanations

    keywords and components related to Android 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
    idl
    -0.08
    coles
    -0.07
    inctions
    -0.07
     cent
    -0.06
    ×ķ
    -0.06
    ãĤ¢ãĥ¼
    -0.06
    instein
    -0.06
    inning
    -0.06
    emen
    -0.06
    \OptionsResolver
    -0.06
    POSITIVE LOGITS
    .os
    0.07
    leh
    0.06
    uiltin
    0.06
    utsch
    0.06
    اÙħÛĮ
    0.06
    ysis
    0.06
    SYS
    0.06
     dsp
    0.06
    ÃŃnÄĽ
    0.06
     defe
    0.05
    Activations Density 0.001%

    No Known Activations