© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 105352
    Prev
    Next
    INDEX
    Explanations

    references to political candidates and issues surrounding acceptance or denial of ideas and services

    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
    #ad
    -0.07
    115
    -0.07
    uler
    -0.07
    geries
    -0.07
    centration
    -0.07
     Cumhur
    -0.07
    /on
    -0.07
    UIScreen
    -0.07
    ấn
    -0.07
    credits
    -0.07
    POSITIVE LOGITS
     because
    0.12
    because
    0.10
     simply
    0.10
     nor
    0.09
     merely
    0.09
    åĽłä¸º
    0.09
     porque
    0.09
     based
    0.09
    Because
    0.08
     Because
    0.08
    Activations Density 0.029%

    No Known Activations