© 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. 117803
    Prev
    Next
    INDEX
    Explanations

    terms related to social and economic status or identity factors

    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
    arella
    -0.08
    alama
    -0.08
    cape
    -0.08
    izu
    -0.08
    eus
    -0.07
    ORB
    -0.07
    uspend
    -0.07
    ãĥªãĤ¢
    -0.07
    luž
    -0.07
    .localized
    -0.07
    POSITIVE LOGITS
    fel
    0.07
    ocha
    0.06
    onec
    0.06
    夫
    0.06
     Herr
    0.06
     jokes
    0.05
    eco
    0.05
     Burns
    0.05
     flood
    0.05
     Saras
    0.05
    Activations Density 0.001%

    No Known Activations