© 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. 94514
    Prev
    Next
    INDEX
    Explanations

    expressions of existential contemplation and feelings of being overwhelmed

    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
    irit
    -0.07
    splice
    -0.07
    apons
    -0.07
    iface
    -0.06
    riot
    -0.06
    ahn
    -0.06
    imuth
    -0.06
    èħķ
    -0.06
    cestor
    -0.06
     dri
    -0.06
    POSITIVE LOGITS
    ̧
    0.07
     DM
    0.07
    eli
    0.07
    atus
    0.07
     alien
    0.07
    orda
    0.06
     Ur
    0.06
     disadv
    0.06
    iesta
    0.06
    ethe
    0.06
    Activations Density 0.023%

    No Known Activations