© 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. 80531
    Prev
    Next
    INDEX
    Explanations

    concepts related to socialism and its implications

    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
    kol
    -0.07
    ale
    -0.06
    kp
    -0.06
    rosso
    -0.06
    AGO
    -0.06
    пÑĢа
    -0.05
    kle
    -0.05
    нÑıÑĤи
    -0.05
    afa
    -0.05
    leared
    -0.05
    POSITIVE LOGITS
     then
    0.38
    then
    0.33
     THEN
    0.31
     Then
    0.30
    Then
    0.29
     followed
    0.28
    ï¼ĮçĦ¶åIJİ
    0.26
    çĦ¶åIJİ
    0.26
    THEN
    0.26
    _then
    0.25
    Activations Density 0.484%

    No Known Activations