© 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. 9-LLAMASCOPE-RES-131K
    11. 98852
    Prev
    Next
    INDEX
    Explanations

    references to cultural and ethnic identity

    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
    nett
    -0.07
    rox
    -0.06
     =
    -0.06
    rob
    -0.06
    anan
    -0.06
     gut
    -0.05
    eter
    -0.05
     d
    -0.05
    rogen
    -0.05
    anium
    -0.05
    POSITIVE LOGITS
    PickerController
    0.08
    ï¼ł
    0.07
    arLayout
    0.07
    ICAST
    0.07
    ekil
    0.07
    ÅĽmy
    0.07
    usterity
    0.07
    .calls
    0.07
    ÑĥÑĩаÑģ
    0.07
    lion
    0.07
    Activations Density 0.002%

    No Known Activations