© 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. 125785
    Prev
    Next
    INDEX
    Explanations

    the word "the" and variations of descriptive language

    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
    Ñħови
    -0.07
    ìĶ
    -0.07
    ascus
    -0.07
    çݯ
    -0.07
     Sharon
    -0.07
    iao
    -0.06
    aroo
    -0.06
     hale
    -0.06
    ãĥ´
    -0.06
    zie
    -0.06
    POSITIVE LOGITS
    ores
    0.06
     stories
    0.06
    Obsolete
    0.06
    ayı
    0.06
     tales
    0.06
     story
    0.06
     tale
    0.06
     Sultan
    0.06
    InputBorder
    0.06
     tert
    0.06
    Activations Density 0.009%

    No Known Activations