© 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. 85093
    Prev
    Next
    INDEX
    Explanations

    references to the New York Times

    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
    afari
    -0.07
    edl
    -0.07
    ieee
    -0.07
    apper
    -0.07
    abez
    -0.06
    erd
    -0.06
    .utility
    -0.06
    ninger
    -0.06
    oji
    -0.06
    acf
    -0.06
    POSITIVE LOGITS
     bestselling
    0.08
    Deserialize
    0.07
     reporters
    0.06
    ãģĤãģĴ
    0.06
    .gov
    0.06
     reporter
    0.06
     columnist
    0.06
    PEND
    0.06
     Adult
    0.06
    ãĥĥ
    0.06
    Activations Density 0.001%

    No Known Activations