© 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. 78923
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that."

    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
    Ùĩ
    -0.08
    ãģĤãģ£ãģŁ
    -0.07
    ãģĤãĤĬ
    -0.07
    verty
    -0.07
    ãģĤãĤĭ
    -0.07
    anity
    -0.07
    esktop
    -0.07
    ously
    -0.06
    alties
    -0.06
    ense
    -0.06
    POSITIVE LOGITS
    abouts
    0.12
    away
    0.10
    ched
    0.10
    -quarters
    0.09
    麼
    0.09
    ching
    0.09
    iban
    0.09
    quarters
    0.08
    chers
    0.08
    aways
    0.08
    Activations Density 0.024%

    No Known Activations