© 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 EvalsExportsAPI 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. 106695
    Prev
    Next
    INDEX
    Explanations

    references to placeholders or empty content in contexts like web pages or articles

    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
    yl
    -0.06
    jo
    -0.06
    –
    -0.06
    -0.06
    -
    -0.05
    elen
    -0.05
    âĢij
    -0.05
     League
    -0.05
     Hong
    -0.05
    ierre
    -0.05
    POSITIVE LOGITS
    antes
    0.09
    lings
    0.08
    -transitional
    0.07
    URLException
    0.07
    eature
    0.07
    Fcn
    0.07
    ubu
    0.07
    uD
    0.07
    NewProp
    0.07
    å°ļ
    0.07
    Activations Density 0.002%

    No Known Activations