© 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. 14618
    Prev
    Next
    INDEX
    Explanations

    themes related to nationality and cultural 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
    gere
    -0.06
    EDGE
    -0.06
     conject
    -0.06
     priorit
    -0.05
     bic
    -0.05
    eph
    -0.05
    af
    -0.05
    ackle
    -0.05
     scarce
    -0.05
    eldon
    -0.05
    POSITIVE LOGITS
    OfType
    0.07
    izin
    0.07
    ãģijãĤĮãģ©
    0.07
    ãĥĪãĥ«
    0.07
    ãĥ¼ãĥĪ
    0.07
    hev
    0.07
     chân
    0.07
     cÆ°
    0.06
    Ù©
    0.06
    oupon
    0.06
    Activations Density 0.001%

    No Known Activations