© 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. 29318
    Prev
    Next
    INDEX
    Explanations

    references to specific overlapping themes or entities, particularly in educational and medical contexts

    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
     ar
    -0.07
    _ASSUME
    -0.06
    ville
    -0.06
    DT
    -0.06
    idge
    -0.06
    idget
    -0.06
     med
    -0.06
     aspect
    -0.06
     aspects
    -0.06
     grátis
    -0.05
    POSITIVE LOGITS
    ожд
    0.07
    587
    0.06
    117
    0.06
    оза
    0.06
    724
    0.06
    469
    0.06
    uffs
    0.06
    (final
    0.06
    resar
    0.06
     ê°ķ
    0.06
    Activations Density 0.003%

    No Known Activations