© 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. 29947
    Prev
    Next
    INDEX
    Explanations

    references to social media and online content engagement

    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
    enie
    -0.06
    ams
    -0.06
    utter
    -0.06
    han
    -0.06
    ached
    -0.05
    aren
    -0.05
     Ha
    -0.05
    æĢ¥
    -0.05
    dictions
    -0.05
    _authenticated
    -0.05
    POSITIVE LOGITS
     subscribe
    0.09
     غر
    0.08
    subscribe
    0.08
    .Subscribe
    0.08
    iasi
    0.08
     subscribing
    0.07
    scribe
    0.07
    çĴ
    0.07
     Subscribe
    0.07
    Subscribe
    0.07
    Activations Density 0.014%

    No Known Activations