© 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 EvalsExportsinterp-engineNEWAPI 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. 54903
    Prev
    Next
    INDEX
    Explanations

    the keyword "supreme" or related forms, indicating a focus on authority or high status

    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
    üst
    -0.08
    ystone
    -0.08
    ypad
    -0.07
    eras
    -0.07
    Margins
    -0.07
    culate
    -0.07
    tags
    -0.07
    cores
    -0.07
    üs
    -0.07
    strap
    -0.07
    POSITIVE LOGITS
     sup
    0.08
    posed
    0.07
    ál
    0.07
     Sup
    0.07
    cial
    0.07
    intendent
    0.07
     dụng
    0.07
    posing
    0.07
    urb
    0.07
    andard
    0.06
    Activations Density 0.014%

    No Known Activations