© 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. 1657
    Prev
    Next
    INDEX
    Explanations

    demographic details related to age and gender

    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
    ona
    -0.08
    ONA
    -0.07
    æĹıèĩªæ²»
    -0.06
    deniz
    -0.06
    awy
    -0.06
    اط
    -0.06
    æk
    -0.06
    isque
    -0.06
    eki
    -0.06
    ledon
    -0.06
    POSITIVE LOGITS
     age
    0.10
     vÄĽku
    0.08
     younger
    0.08
     older
    0.08
    å¹´é¾Ħ
    0.08
     ages
    0.08
     tuá»ķi
    0.08
    è¡
    0.08
    .age
    0.07
     somewhere
    0.07
    Activations Density 0.016%

    No Known Activations