© 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. 76546
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal expectations and cultural pressures

    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
    mes
    -0.07
    thal
    -0.06
     McKenzie
    -0.06
     ch
    -0.06
    adem
    -0.05
    aign
    -0.05
     Kem
    -0.05
    ater
    -0.05
    äºĭ
    -0.05
    oples
    -0.05
    POSITIVE LOGITS
    ambre
    0.08
     ?>"/>↵
    0.07
    ablish
    0.07
    decorators
    0.07
    ucci
    0.07
    -ÑĤо
    0.07
    reshold
    0.07
    ÙĬار
    0.07
     itself
    0.06
    hyth
    0.06
    Activations Density 0.045%

    No Known Activations