© 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. 40053
    Prev
    Next
    INDEX
    Explanations

    phrases concerning personal actions and preferences

    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
     beyond
    -0.08
     Beyond
    -0.07
     very
    -0.06
    ela
    -0.06
     quite
    -0.06
    ptr
    -0.06
    Beyond
    -0.06
     oltre
    -0.06
     kolej
    -0.06
    akan
    -0.06
    POSITIVE LOGITS
     than
    0.18
    than
    0.16
     rather
    0.13
     THAN
    0.13
     Than
    0.13
    _than
    0.12
    Than
    0.12
    rather
    0.11
    -than
    0.11
    Rather
    0.11
    Activations Density 0.039%

    No Known Activations