© 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. 18575
    Prev
    Next
    INDEX
    Explanations

    references to social media interactions and user data

    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
    adle
    -0.07
     znal
    -0.07
    anches
    -0.07
    วà¸ģ
    -0.07
    _mC
    -0.07
     simd
    -0.07
    bourg
    -0.07
    _fsm
    -0.07
    ouncement
    -0.07
    _PCM
    -0.07
    POSITIVE LOGITS
    orsch
    0.06
     vulnerability
    0.06
     vulnerable
    0.06
     compromised
    0.06
     possibly
    0.06
     addresses
    0.06
     Kraft
    0.06
     Vulner
    0.06
     branch
    0.05
     Reconstruction
    0.05
    Activations Density 0.002%

    No Known Activations