© 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. 9-LLAMASCOPE-RES-131K
    11. 97792
    Prev
    Next
    INDEX
    Explanations

    references to historical buildings and their modifications

    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
    auf
    -0.07
    /Internal
    -0.06
    byn
    -0.06
    holm
    -0.06
    овÑĥ
    -0.06
    BERT
    -0.06
    redd
    -0.06
    IT
    -0.06
     Britt
    -0.06
    arendra
    -0.06
    POSITIVE LOGITS
    _extraction
    0.06
    ipes
    0.06
     mixed
    0.06
    orno
    0.06
    .timeout
    0.06
     fire
    0.06
    eyen
    0.06
    activex
    0.06
     uns
    0.06
    isting
    0.06
    Activations Density 0.117%

    No Known Activations