© 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. 85199
    Prev
    Next
    INDEX
    Explanations

    discussions about social media and its integration into society

    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
     recent
    -0.10
    recent
    -0.09
     recently
    -0.09
     lately
    -0.08
    Ïģά
    -0.08
     Recently
    -0.08
     Recent
    -0.08
    Recently
    -0.08
    Recent
    -0.07
     è¿ij
    -0.07
    POSITIVE LOGITS
     someday
    0.09
     will
    0.07
     instead
    0.07
    etto
    0.07
    /rfc
    0.07
     eventually
    0.07
     Routine
    0.07
    azz
    0.07
     become
    0.07
    -нибÑĥдÑĮ
    0.07
    Activations Density 0.052%

    No Known Activations