© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18001
    Prev
    Next
    INDEX
    Explanations

    mentions of social media engagement and online interactions

    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
     оÑĩ
    -0.07
    Animations
    -0.06
    ampoo
    -0.06
    umpt
    -0.06
     Wiki
    -0.06
    izoph
    -0.06
    iefs
    -0.06
    Hostname
    -0.06
    oire
    -0.06
    anke
    -0.06
    POSITIVE LOGITS
     twitter
    0.14
     Twitter
    0.14
     (@
    0.14
     Instagram
    0.14
     facebook
    0.13
     Facebook
    0.13
    twitter
    0.13
     social
    0.12
     followers
    0.12
     instagram
    0.12
    Activations Density 0.394%

    No Known Activations