© 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. 95904
    Prev
    Next
    INDEX
    Explanations

    references to political themes and societal structures

    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
    iros
    -0.06
     Ob
    -0.06
    intl
    -0.05
     Cruc
    -0.05
    rne
    -0.05
    оÑī
    -0.05
     Dro
    -0.05
    vil
    -0.05
    TimeString
    -0.05
    าà¸ĩ
    -0.05
    POSITIVE LOGITS
     now
    0.28
    now
    0.24
    -now
    0.23
     ahora
    0.22
     Now
    0.21
    Now
    0.21
    _now
    0.20
     ÑĤепеÑĢÑĮ
    0.20
     NOW
    0.19
    çİ°åľ¨
    0.19
    Activations Density 0.064%

    No Known Activations