© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 96078
    Prev
    Next
    INDEX
    Explanations

    phrases related to digital communication and online interactions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    utz
    -0.07
    ecute
    -0.06
    etch
    -0.06
    ufe
    -0.06
    tile
    -0.06
    atham
    -0.06
     pursuit
    -0.06
     etc
    -0.06
     especially
    -0.06
    оÑĢаз
    -0.06
    POSITIVE LOGITS
     therefore
    0.10
     thus
    0.09
     consequently
    0.08
     hence
    0.08
     Therefore
    0.08
    ï¼ĮåĽłæѤ
    0.08
     donc
    0.07
    Thus
    0.07
     wiÄĻc
    0.07
     addslashes
    0.07
    Activations Density 0.044%

    No Known Activations