© 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. 39193
    Prev
    Next
    INDEX
    Explanations

    references to personal and professional backgrounds related to political or artistic contexts

    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
    uat
    -0.07
    acht
    -0.07
    aine
    -0.07
    ones
    -0.07
    çĬ
    -0.07
    ovel
    -0.07
    .intValue
    -0.07
    ضاÙĨ
    -0.06
    лок
    -0.06
    aptop
    -0.06
    POSITIVE LOGITS
    以åıĬ
    0.07
    REQUIRED
    0.07
    à¹ģละà¸ģาร
    0.07
     years
    0.06
     kariy
    0.06
    AYS
    0.06
     Cooke
    0.06
    .fhir
    0.06
    /Peak
    0.06
    ï¼Į以åıĬ
    0.06
    Activations Density 0.037%

    No Known Activations