© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 59208
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals, particularly in the context of events or circumstances surrounding their lives or deaths

    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
     had
    -0.06
     ones
    -0.06
     ds
    -0.06
    indsight
    -0.06
    اÙĦØ©
    -0.06
    ers
    -0.06
    Į
    -0.06
    ,
    -0.05
     Pall
    -0.05
     '\'
    -0.05
    POSITIVE LOGITS
     whose
    0.09
    åıĬåħ¶
    0.08
    ityEngine
    0.08
    whose
    0.08
    ioned
    0.08
    ieber
    0.08
    ritte
    0.07
    WXYZ
    0.07
     jehož
    0.07
    :animated
    0.07
    Activations Density 0.027%

    No Known Activations