© 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. 5-LLAMASCOPE-RES-131K
    11. 125534
    Prev
    Next
    INDEX
    Explanations

    the use of the word "basically" as a summarizing or explanatory term

    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
    cu
    -0.06
     kup
    -0.06
    edic
    -0.06
    cest
    -0.06
    sson
    -0.05
    å¾Ĵ
    -0.05
    Valor
    -0.05
    illard
    -0.05
    ij
    -0.05
     micro
    -0.05
    POSITIVE LOGITS
    거리
    0.08
    ../../../../
    0.08
    ãĥ¡ãĥ³ãĥĪ
    0.07
    asters
    0.07
    ÑĤÑİ
    0.07
    porto
    0.07
    heed
    0.07
     (*)(
    0.07
    ¢åįķ
    0.07
    ially
    0.07
    Activations Density 0.005%

    No Known Activations