© 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. 77312
    Prev
    Next
    INDEX
    Explanations

    references to gender inequalities and societal expectations

    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
    icari
    -0.10
    arget
    -0.09
    indir
    -0.08
    รม
    -0.08
    aris
    -0.08
    allah
    -0.08
    ãĤĤãĤĬ
    -0.08
    aç
    -0.08
    onse
    -0.08
    anzi
    -0.07
    POSITIVE LOGITS
     male
    0.24
     males
    0.20
     Male
    0.18
    male
    0.18
    çĶ·æĢ§
    0.16
     masculine
    0.16
    Male
    0.15
     men
    0.14
     мÑĥжÑĩин
    0.14
     mascul
    0.14
    Activations Density 0.032%

    No Known Activations