© 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. 15-LLAMASCOPE-RES-131K
    11. 27347
    Prev
    Next
    INDEX
    Explanations

    instances of emotional engagement or reactions to personal experiences

    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
    ankan
    -0.07
    ullan
    -0.06
    aggio
    -0.06
    زاÙĨ
    -0.06
    lok
    -0.06
    ervo
    -0.06
    elope
    -0.06
    ãģļ
    -0.06
    yle
    -0.06
     Foto
    -0.06
    POSITIVE LOGITS
    Æ°á»Łng
    0.08
    wap
    0.07
    orte
    0.07
    ÏĢιÏĥ
    0.06
    orian
    0.06
     Cra
    0.06
    лиÑĤ
    0.06
    kdir
    0.06
     pavement
    0.06
    eum
    0.06
    Activations Density 0.063%

    No Known Activations