© 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. 127116
    Prev
    Next
    INDEX
    Explanations

    references to excessive or overwhelming qualities

    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
    eding
    -0.06
    245
    -0.06
     alot
    -0.06
    odb
    -0.06
     specially
    -0.06
    hire
    -0.06
     lots
    -0.05
     fortunes
    -0.05
    ilo
    -0.05
     gre
    -0.05
    POSITIVE LOGITS
    ahn
    0.09
    unden
    0.08
    ucas
    0.08
    busy
    0.07
    esk
    0.07
    AccessType
    0.07
    æļ
    0.07
    /goto
    0.07
    tml
    0.07
    기를
    0.07
    Activations Density 0.012%

    No Known Activations