© 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. 89625
    Prev
    Next
    INDEX
    Explanations

    references to file structures or programming syntax

    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
    даÑĤ
    -0.07
    iegel
    -0.07
    Äįer
    -0.07
     lúc
    -0.06
    ancel
    -0.06
    als
    -0.06
    룴
    -0.06
     ë§Īì§Ģë§ī
    -0.06
     Disposable
    -0.06
    å
    -0.06
    POSITIVE LOGITS
    ahun
    0.07
    акÑģим
    0.07
    achs
    0.06
    nts
    0.06
    endance
    0.06
    ampion
    0.06
    strar
    0.06
    293
    0.06
    δή
    0.06
    avir
    0.06
    Activations Density 0.001%

    No Known Activations