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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28674
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions or occurrences

    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
    raud
    -0.08
    .masks
    -0.07
    kel
    -0.07
    figcaption
    -0.07
    aled
    -0.07
    nett
    -0.07
    kie
    -0.07
    INE
    -0.07
    ptest
    -0.07
    inkel
    -0.07
    POSITIVE LOGITS
     when
    0.10
     either
    0.09
     whenever
    0.09
     usually
    0.07
    when
    0.07
     after
    0.07
     basically
    0.07
    omat
    0.07
     AFTER
    0.06
     often
    0.06
    Activations Density 0.037%

    No Known Activations