© 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. 17-LLAMASCOPE-RES-131K
    11. 130286
    Prev
    Next
    INDEX
    Explanations

    inquiries and discussions about abstract concepts and their significance

    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
    illin
    -0.07
    earer
    -0.07
    ixin
    -0.07
    alli
    -0.06
    asInstanceOf
    -0.06
    antan
    -0.06
    ë°©
    -0.06
     whilst
    -0.06
    cki
    -0.06
    oui
    -0.06
    POSITIVE LOGITS
    ichert
    0.07
     PTR
    0.06
    omite
    0.06
    enha
    0.06
    anga
    0.06
    atto
    0.06
    mium
    0.06
     z
    0.06
     erót
    0.06
    ture
    0.06
    Activations Density 0.002%

    No Known Activations