© 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. 84910
    Prev
    Next
    INDEX
    Explanations

    concepts related to interdisciplinary themes and the blending of different fields or genres

    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
    hof
    -0.08
    éro
    -0.07
    oba
    -0.07
    tak
    -0.07
    loor
    -0.07
    orz
    -0.07
    éri
    -0.06
     merk
    -0.06
    loh
    -0.06
     duplicates
    -0.06
    POSITIVE LOGITS
     disciplinary
    0.09
     crossing
    0.08
     cross
    0.08
     disciplines
    0.08
     crosses
    0.08
    cross
    0.07
    _cross
    0.07
     crossover
    0.07
     crossings
    0.07
     Crossing
    0.07
    Activations Density 0.031%

    No Known Activations