© 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. 120778
    Prev
    Next
    INDEX
    Explanations

    words related to emotional states and reflections on life 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
    anj
    -0.07
    opo
    -0.06
    urs
    -0.06
    ston
    -0.06
    ulan
    -0.06
     this
    -0.06
    croft
    -0.06
    irk
    -0.06
    him
    -0.06
     edition
    -0.06
    POSITIVE LOGITS
     sometimes
    0.12
    sometimes
    0.10
    Sometimes
    0.10
     Sometimes
    0.09
    ometimes
    0.09
     bazen
    0.08
     often
    0.08
     иногда
    0.07
    often
    0.07
    OMET
    0.07
    Activations Density 0.024%

    No Known Activations