© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 58089
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitions that indicate contrast or complexity in statements

    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
    ily
    -0.07
    iler
    -0.06
    ks
    -0.06
    ("(%
    -0.06
    osta
    -0.06
    ially
    -0.06
     mol
    -0.06
    ÃŃ
    -0.06
    elper
    -0.06
    idata
    -0.06
    POSITIVE LOGITS
    jang
    0.07
    é¹
    0.07
    .uni
    0.07
    adir
    0.07
    iddi
    0.07
    ajaran
    0.07
    ogie
    0.07
    vyk
    0.07
    umas
    0.07
    BackingField
    0.07
    Activations Density 0.047%

    No Known Activations