© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83625
    Prev
    Next
    INDEX
    Explanations

    references to male characters and their attributes or roles

    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
    rame
    -0.07
    ichert
    -0.07
    #af
    -0.07
    reuse
    -0.07
    .nano
    -0.07
    #ae
    -0.07
    maal
    -0.07
     personalities
    -0.06
    grp
    -0.06
     mutual
    -0.06
    POSITIVE LOGITS
     himself
    0.09
    妻
    0.09
     his
    0.08
    -wife
    0.06
     wife
    0.06
     seinem
    0.06
     whom
    0.06
    his
    0.06
    ìĦ¸
    0.06
    .libs
    0.06
    Activations Density 0.043%

    No Known Activations