© 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. 9-LLAMASCOPE-RES-131K
    11. 96687
    Prev
    Next
    INDEX
    Explanations

    keywords relating to personal relationships and emotions

    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
     Celt
    -0.08
    Ïħμ
    -0.08
    omik
    -0.08
    .struts
    -0.08
     شر
    -0.07
    akin
    -0.07
    à¥Ľ
    -0.07
    оÑĤÑĮ
    -0.07
    à¥ģश
    -0.07
    UMB
    -0.07
    POSITIVE LOGITS
    iosper
    0.06
    ãĥ¼ãĥĹ
    0.06
    ysqli
    0.06
    ongyang
    0.06
    ingroup
    0.06
    upd
    0.06
     Lawson
    0.06
    pcl
    0.06
    ymce
    0.06
    262
    0.05
    Activations Density 0.101%

    No Known Activations