© 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. 61498
    Prev
    Next
    INDEX
    Explanations

    instances of possessive forms related to the present day and contemporary topics

    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
    ussen
    -0.09
    aku
    -0.07
     sooner
    -0.07
    lich
    -0.06
    ally
    -0.06
    ered
    -0.06
     lately
    -0.06
    Ì
    -0.06
    uit
    -0.06
    conde
    -0.06
    POSITIVE LOGITS
    -day
    0.08
     modern
    0.08
    modern
    0.08
    avia
    0.07
    -era
    0.07
    asser
    0.07
     moden
    0.07
    Ùħار
    0.07
    ëĤł
    0.07
    anou
    0.07
    Activations Density 0.003%

    No Known Activations