© 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. 22
    Prev
    Next
    INDEX
    Explanations

    phrases indicating online engagement or interaction

    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
    /utility
    -0.07
    roi
    -0.07
    åĥķ
    -0.07
    ÏĦÏį
    -0.07
    reste
    -0.07
    ities
    -0.07
    TouchEvent
    -0.07
    angu
    -0.06
    OLUMNS
    -0.06
    LK
    -0.06
    POSITIVE LOGITS
     Frag
    0.06
     Col
    0.06
     frag
    0.06
     vie
    0.05
     Joanna
    0.05
     follow
    0.05
     eldre
    0.05
    ëĿ½
    0.05
     Vernon
    0.05
    ektor
    0.05
    Activations Density 0.000%

    No Known Activations