© 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. 126661
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to specific names or references, particularly those involving the letter sequences "ee" or "Dee."

    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
    st
    -0.09
    ous
    -0.07
    y
    -0.07
    tt
    -0.07
    tn
    -0.07
    ÙĦÙģ
    -0.07
    tro
    -0.07
    kke
    -0.07
    ми
    -0.06
    ãģĦãĤĭ
    -0.06
    POSITIVE LOGITS
    kest
    0.09
    ajas
    0.08
    bles
    0.08
    zers
    0.07
    uw
    0.07
    zy
    0.07
    ahoo
    0.07
    Ø¡
    0.07
    ahn
    0.07
    oop
    0.07
    Activations Density 0.028%

    No Known Activations