© 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. 9-LLAMASCOPE-RES-131K
    11. 99280
    Prev
    Next
    INDEX
    Explanations

    themes related to social challenges and restrictions on personal freedom

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Ñİк
    -0.07
    uto
    -0.07
    ells
    -0.06
    iku
    -0.06
    elsif
    -0.06
    awks
    -0.06
    ihu
    -0.06
     Russell
    -0.06
    çīĻ
    -0.06
    ELS
    -0.06
    POSITIVE LOGITS
    aroo
    0.06
     dereg
    0.06
    सर
    0.06
    eração
    0.06
     modern
    0.06
    ÏģÏį
    0.06
     миÑģÑĤ
    0.05
    าระ
    0.05
    aspers
    0.05
    _then
    0.05
    Activations Density 0.092%

    No Known Activations